{"id":16674,"date":"2024-01-24T04:55:00","date_gmt":"2024-01-24T04:55:00","guid":{"rendered":"https:\/\/blog.datumo.com\/en\/?p=16674"},"modified":"2024-10-22T09:06:44","modified_gmt":"2024-10-22T09:06:44","slug":"depth-estimation-marigold","status":"publish","type":"post","link":"https:\/\/blog.datumo.com\/en\/tech\/16674","title":{"rendered":"The Most Refined Depth Estimation Model: Marigold"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"16674\" class=\"elementor elementor-16674\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-5b3d72c elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"5b3d72c\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-e21b07\" data-id=\"e21b07\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-13eac76 elementor-widget elementor-widget-text-editor\" data-id=\"13eac76\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.23.0 - 05-08-2024 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#69727d;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#69727d;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<h1><span style=\"font-weight: bolder;\"><span style=\"font-family: helvetica, arial, sans-serif;\"><span style=\"font-size: 16px;\">Depth Estimation SOTA Model Using Stable Diffusion: Marigold<\/span><\/span><\/span><\/h1><p><span style=\"color: inherit; font-family: helvetica, arial, sans-serif; font-size: 12pt; letter-spacing: -0.01em;\">While NLP is advancing so quickly, what about other fields? The release of text-to-image models in 2022 marked the mainstream adoption of generative AI. Models like MidJourney and DALL-E generated excitement with their capabilities and have since paved the way for advancements in models that generate not only images but also videos and 3D content.<\/span><\/p><p><span style=\"font-size: 12pt; font-family: helvetica, arial, sans-serif;\">Today, we introduce Marigold, a model that has achieved state-of-the-art (SOTA) results in depth estimation using Stable Diffusion<\/span><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt; color: inherit; letter-spacing: -0.01em;\">.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-3458d5b4 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"3458d5b4\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-390609c6\" data-id=\"390609c6\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-6499aca9 elementor-widget elementor-widget-pix-heading\" data-id=\"6499aca9\" data-element_type=\"widget\" data-widget_type=\"pix-heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div  class=\"pix-heading-el text-center \"><div><div class=\"slide-in-container\"><h3 class=\"font-weight-bold heading-text el-title_custom_color mb-12\" style=\"\" data-anim-type=\"\" data-anim-delay=\"\">Depth Estimation Models<\/h3><\/div><\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-555643af elementor-widget elementor-widget-text-editor\" data-id=\"555643af\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<meta http-equiv=\"refresh\" content=\"0; url=https:\/\/datumo.com\/en\/depth-estimation-marigold\/\">\n\n<span style=\"color: #5c5c5c; font-family: helvetica, arial, sans-serif;\"><span style=\"font-size: 16px;\">For those unfamiliar with computer vision, the term &#8220;depth estimation&#8221; might be new. Depth, in this context, refers to the perceived distance between objects. While we know that photos are two-dimensional, we can still estimate how far objects are from each other within an image. Objects of the same size will appear larger when closer and smaller when farther away. Depth estimation, as a field of vision technology, involves determining the depth information of a three-dimensional space from a two-dimensional image.<\/span><\/span>\n\n<span style=\"color: #5c5c5c; font-family: helvetica, arial, sans-serif;\"><span style=\"font-size: 16px;\">The technology can be applied in various industries. For instance, consider how a self-driving car might recognize surrounding objects using only a camera without additional sensors. While the car can identify objects from a 2D image, it cannot easily determine the distance between the vehicle and those objects. In such cases, depth estimation can be utilized to estimate these distances based solely on the 2D image.<\/span><\/span>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7b3e75d8 elementor-widget elementor-widget-image\" data-id=\"7b3e75d8\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.23.0 - 05-08-2024 *\/\n.elementor-widget-image{text-align:center}.elementor-widget-image a{display:inline-block}.elementor-widget-image a img[src$=\".svg\"]{width:48px}.elementor-widget-image img{vertical-align:middle;display:inline-block}<\/style>\t\t\t\t\t\t\t\t\t\t\t<a href=\"https:\/\/marigoldmonodepth.github.io\/\">\n\t\t\t\t\t\t\t<img fetchpriority=\"high\" decoding=\"async\" width=\"640\" height=\"212\" src=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.17.38-1024x339.jpg\" class=\"attachment-large size-large wp-image-16683\" alt=\"\" srcset=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.17.38-1024x339.jpg 1024w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.17.38-300x99.jpg 300w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.17.38-768x254.jpg 768w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.17.38-1536x508.jpg 1536w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.17.38.jpg 1920w\" sizes=\"(max-width: 640px) 100vw, 640px\" \/>\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-5957652f elementor-widget elementor-widget-pix-text\" data-id=\"5957652f\" data-element_type=\"widget\" data-widget_type=\"pix-text.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div class=\"pix-el-text w-100 text-center \" ><p class=\"text-xs  text-gray-6 text-center font-weight-bold font-italic\" >Source: Digging Into Self-Supervised Monocular Depth Estimation (Godard et al., 2018)<\/p><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-62e0da2a elementor-widget elementor-widget-text-editor\" data-id=\"62e0da2a\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\">Let\u2019s take a closer look at depth estimation technology. How do humans perceive the distance of objects? We see the world with two eyes, each capturing slightly different visual information. Our brains interpret this difference in visual information as depth. Similarly, in computer vision, two or more cameras can be used to capture the same scene from different angles. By comparing these images, depth can be estimated. This is known as <strong>binocular depth estimation<\/strong>.<\/span><\/p><p><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\">However, humans can also estimate distance with just one eye. We rely on the visual size of objects and accumulated experiential knowledge to estimate distance. Computers can do the same. When estimating distance from a single 2D image, this falls under the category of <strong>monocular depth estimation<\/strong>.<\/span><!-- notionvc: 31795f04-3a43-4a63-9b7f-e2ef74f673ec --><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-4dda49a elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"4dda49a\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-fe0f17d\" data-id=\"fe0f17d\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-c66060e elementor-widget elementor-widget-pix-heading\" data-id=\"c66060e\" data-element_type=\"widget\" data-widget_type=\"pix-heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div  class=\"pix-heading-el text-center \"><div><div class=\"slide-in-container\"><h3 class=\"font-weight-bold heading-text el-title_custom_color mb-12\" style=\"\" data-anim-type=\"\" data-anim-delay=\"\">The Principle and Structure of Marigold Using Stable Diffusion<\/h3><\/div><\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c7d024f elementor-widget elementor-widget-image\" data-id=\"c7d024f\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"640\" height=\"318\" src=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.21.56-1024x508.jpg\" class=\"attachment-large size-large wp-image-16684\" alt=\"\" srcset=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.21.56-1024x508.jpg 1024w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.21.56-300x149.jpg 300w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.21.56-768x381.jpg 768w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.21.56-1536x762.jpg 1536w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_12.21.56.jpg 1920w\" sizes=\"(max-width: 640px) 100vw, 640px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1ea32b4 elementor-widget elementor-widget-pix-text\" data-id=\"1ea32b4\" data-element_type=\"widget\" data-widget_type=\"pix-text.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div class=\"pix-el-text w-100 text-center \" ><p class=\"text-xs  text-gray-6 text-center font-weight-bold font-italic\" >Source: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (Ke et al., 2023)<\/p><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b313ced elementor-widget elementor-widget-text-editor\" data-id=\"b313ced\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p style=\"text-align: left;\"><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\">Marigold focuses on monocular depth estimation, meaning it can generate a depth map from a single 2D image. To achieve this, a significant amount of information must be accumulated, including experiential data about objects in the image, segmentation between objects, separation of objects from the background, and relative depth perception based on visual size.<\/span><\/p>\n<p><span style=\"font-size: 12pt;\"><span style=\"font-family: helvetica, arial, sans-serif;\">The Marigold model was introduced in the paper <strong>Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation<\/strong>, published in December 2023. Marigold is unlike traditional methods. It integrates diffusion-based models, typically used for image generation, into the field of depth estimation. The researchers&#8217; idea was as follows:<\/span><!-- notionvc: b7dcd185-cf55-49ba-a29d-eef82959385c --><\/span><\/p>\n<blockquote>\n<p><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\"> <span role=\"img\" aria-label=\"\ud83e\uddd1\u200d\ud83c\udfeb\"><img decoding=\"async\" class=\"emoji\" role=\"img\" draggable=\"false\" src=\"https:\/\/s.w.org\/images\/core\/emoji\/15.0.3\/svg\/1f9d1-200d-1f3eb.svg\" alt=\"\ud83e\uddd1\u200d\ud83c\udfeb\"> <\/span><!-- notionvc: f3670bcd-61b1-492c-9f4d-ca34a4d40010 -->If image generation models have already learned high-quality images from various domains uploaded to the internet, could this be applied to depth estimation?<!-- notionvc: 02873d21-4a53-4cc9-8648-c994cc5c4e45 --><\/span><\/p>\n<\/blockquote>\n<p><span style=\"font-size: 12pt;\"><span style=\"font-family: helvetica, arial, sans-serif;\">Thus, Marigold leverages the pre-trained capabilities of Stable Diffusion. To adapt this generative model for depth estimation, fine-tuning is required.<!-- notionvc: 377c9e52-404e-4f71-ab86-8780bd781844 --><\/span><span style=\"font-family: helvetica, arial, sans-serif;\">&nbsp;<\/span><\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-a414734 elementor-widget elementor-widget-image\" data-id=\"a414734\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"640\" height=\"353\" src=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.49-1024x564.jpg\" class=\"attachment-large size-large wp-image-16688\" alt=\"\" srcset=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.49-1024x564.jpg 1024w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.49-300x165.jpg 300w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.49-768x423.jpg 768w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.49-1536x846.jpg 1536w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.49.jpg 1870w\" sizes=\"(max-width: 640px) 100vw, 640px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3ef5700 elementor-widget elementor-widget-pix-text\" data-id=\"3ef5700\" data-element_type=\"widget\" data-widget_type=\"pix-text.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div class=\"pix-el-text w-100 text-center \" ><p class=\"text-xs  text-gray-6 text-center font-weight-bold font-italic\" >Source: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (Ke et al., 2023)<\/p><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7113cea elementor-widget elementor-widget-text-editor\" data-id=\"7113cea\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\">The fine-tuning structure is shown in the image above. Using a VAE, the real image and the depth map, as well as their respective encodings into latent space, are processed. Noise is added to the depth map and the two images are concatenated. The diffusion model then removes the noise to generate the depth map again. This process utilizes the training principles of the latent diffusion model that underpins Stable Diffusion, but specifically tailored to generate depth maps.<\/span><\/p><p><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\">To enhance training performance, synthetic data is used. Rather than relying on datasets with real depth values, synthetic data is preferred due to the physical limitations that can reduce the accuracy of real data.<\/span><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4002148 elementor-widget elementor-widget-image\" data-id=\"4002148\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"640\" height=\"314\" src=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.58-1024x503.jpg\" class=\"attachment-large size-large wp-image-16689\" alt=\"\" srcset=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.58-1024x503.jpg 1024w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.58-300x147.jpg 300w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.58-768x377.jpg 768w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.58-1536x755.jpg 1536w, https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/08\/E18489E185B3E1848FE185B3E18485E185B5E186ABE18489E185A3E186BA_2024-01-17_E1848BE185A9E18492E185AE_1.53.58.jpg 1876w\" sizes=\"(max-width: 640px) 100vw, 640px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6b075eb elementor-widget elementor-widget-pix-text\" data-id=\"6b075eb\" data-element_type=\"widget\" data-widget_type=\"pix-text.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div class=\"pix-el-text w-100 text-center \" ><p class=\"text-xs  text-gray-6 text-center font-weight-bold font-italic\" >Source: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (Ke et al., 2023)<\/p><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0452d75 elementor-widget elementor-widget-text-editor\" data-id=\"0452d75\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\">Once fine-tuning is complete, the inference structure follows a similar process. Noise is added and removed from the original image, and the final image is decoded to produce a high-resolution depth map.<\/span><!-- notionvc: 996a3354-0b8c-4c41-b752-bf2b8591c562 --><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-79b19a05 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"79b19a05\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-15dc7051\" data-id=\"15dc7051\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-78f852d0 elementor-widget elementor-widget-text-editor\" data-id=\"78f852d0\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\">Marigold has achieved SOTA results in the field of depth estimation and excels in zero-shot performance. This means it produces impressive results even on previously unseen data. The generated depth maps accurately delineate object boundaries within images and align well with human intuition.<\/span><\/p><p><span style=\"font-family: helvetica, arial, sans-serif; font-size: 12pt;\">As hinted by the term &#8220;repurposing&#8221; in the paper&#8217;s title, this work demonstrates how the concept behind diffusion models can be applied to different tasks. This suggests that advancements in one model can be leveraged for various purposes in other fields. Diffusion models, known for their strong performance in image generation, are also being explored for applications in text generation. Even if these initial attempts don&#8217;t immediately yield significant results, the long-term impact of one model&#8217;s research can significantly influence progress in other domains.<\/span><!-- notionvc: 5c2bad5c-726e-4ef6-a1df-8b0876a9c658 --><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-1b970284 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"1b970284\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-4b6b30c0\" data-id=\"4b6b30c0\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-3fe3314e elementor-invisible elementor-widget elementor-widget-pix-heading\" data-id=\"3fe3314e\" data-element_type=\"widget\" data-widget_type=\"pix-heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div  class=\"pix-heading-el text-center \"><div><div class=\"slide-in-container\"><h3 class=\"font-weight-bold animate-in heading-text el-title_custom_color mb-12\" style=\"\" data-anim-type=\"slide-in-up\" data-anim-delay=\"0\">Your AI Data Standard<\/h3><\/div><\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-4f10b584 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"4f10b584\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-top-column elementor-element elementor-element-217419af\" data-id=\"217419af\" data-element_type=\"column\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-1e2788c0 elementor-widget elementor-widget-pix-heading\" data-id=\"1e2788c0\" data-element_type=\"widget\" data-widget_type=\"pix-heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div  class=\"pix-heading-el text-center \"><div><div class=\"slide-in-container\"><h5 class=\"text-white font-weight-bold heading-text el-title_custom_color mb-12\" style=\"\" data-anim-type=\"\" data-anim-delay=\"\">LLM Evaluation Platform<\/h5><\/div><\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2e12231 elementor-widget elementor-widget-pix-button\" data-id=\"2e12231\" data-element_type=\"widget\" data-widget_type=\"pix-button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<span  class=\"btn m-0     text-primary btn-white d-inline-block      btn-normal\"     ><span class=\"font-weight-bold \" >Learn more<\/span> <i class=\"font-weight-bold pixicon-arrow-right2   ml-1\"><\/i><\/span>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-top-column elementor-element elementor-element-1077cbf0\" data-id=\"1077cbf0\" data-element_type=\"column\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-db1cd1a elementor-widget elementor-widget-pix-heading\" data-id=\"db1cd1a\" data-element_type=\"widget\" data-widget_type=\"pix-heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<div  class=\"pix-heading-el text-center \"><div><div class=\"slide-in-container\"><h5 class=\"text-primary font-weight-bold heading-text el-title_custom_color mb-12\" style=\"\" data-anim-type=\"\" data-anim-delay=\"\">About Datumo<\/h5><\/div><\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4b183916 elementor-widget elementor-widget-pix-button\" data-id=\"4b183916\" data-element_type=\"widget\" data-widget_type=\"pix-button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<span  class=\"btn m-0     btn-primary d-inline-block      btn-normal\"     ><span class=\"font-weight-bold \" >Learn more<\/span> <i class=\"font-weight-bold pixicon-arrow-right2   ml-1\"><\/i><\/span>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"Depth Estimation SOTA Model Using Stable Diffusion: MarigoldWhile NLP is advancing so quickly, what about other fields? The release of text-to-image models in 2022 marked the mainstream adoption of generative AI. Models like MidJourney and DALL-E generated excitement with their&#8230;","protected":false},"author":1,"featured_media":16701,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[131],"tags":[],"class_list":["post-16674","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tech"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v23.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>The Most Refined Depth Estimation Model: Marigold - DATUMO<\/title>\n<meta name=\"description\" content=\"Dive into the most refines depth estimation model, Marigold. Marigold, has achieved SOTA results in depth estimation using Stable Diffusion.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/blog.datumo.com\/en\/tech\/16674\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"The Most Refined Depth Estimation Model: Marigold - DATUMO\" \/>\n<meta property=\"og:description\" content=\"Dive into the most refines depth estimation model, Marigold. Marigold, has achieved SOTA results in depth estimation using Stable Diffusion.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/blog.datumo.com\/en\/tech\/16674\" \/>\n<meta property=\"og:site_name\" content=\"DATUMO\" \/>\n<meta property=\"article:published_time\" content=\"2024-01-24T04:55:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-10-22T09:06:44+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1920\" \/>\n\t<meta property=\"og:image:height\" content=\"1440\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"DATUMO\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\uae00\uc4f4\uc774\" \/>\n\t<meta name=\"twitter:data1\" content=\"DATUMO\" \/>\n\t<meta name=\"twitter:label2\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data2\" content=\"6\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674#article\",\"isPartOf\":{\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674\"},\"author\":{\"name\":\"DATUMO\",\"@id\":\"https:\/\/blog.datumo.com\/#\/schema\/person\/02ec2d0ba953b146878dab089dc735b6\"},\"headline\":\"The Most Refined Depth Estimation Model: Marigold\",\"datePublished\":\"2024-01-24T04:55:00+00:00\",\"dateModified\":\"2024-10-22T09:06:44+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674\"},\"wordCount\":842,\"publisher\":{\"@id\":\"https:\/\/blog.datumo.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674#primaryimage\"},\"thumbnailUrl\":\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg\",\"articleSection\":[\"tech\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674\",\"url\":\"https:\/\/blog.datumo.com\/en\/tech\/16674\",\"name\":\"The Most Refined Depth Estimation Model: Marigold - DATUMO\",\"isPartOf\":{\"@id\":\"https:\/\/blog.datumo.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674#primaryimage\"},\"image\":{\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674#primaryimage\"},\"thumbnailUrl\":\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg\",\"datePublished\":\"2024-01-24T04:55:00+00:00\",\"dateModified\":\"2024-10-22T09:06:44+00:00\",\"description\":\"Dive into the most refines depth estimation model, Marigold. Marigold, has achieved SOTA results in depth estimation using Stable Diffusion.\",\"breadcrumb\":{\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/blog.datumo.com\/en\/tech\/16674\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674#primaryimage\",\"url\":\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg\",\"contentUrl\":\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg\",\"width\":1920,\"height\":1440},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/blog.datumo.com\/en\/tech\/16674#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/blog.datumo.com\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"The Most Refined Depth Estimation Model: Marigold\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/blog.datumo.com\/#website\",\"url\":\"https:\/\/blog.datumo.com\/\",\"name\":\"DATUMO\",\"description\":\"The Data for Smarter AI\",\"publisher\":{\"@id\":\"https:\/\/blog.datumo.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/blog.datumo.com\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/blog.datumo.com\/#organization\",\"name\":\"DATUMO\",\"url\":\"https:\/\/blog.datumo.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/blog.datumo.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2022\/05\/2.1.webp\",\"contentUrl\":\"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2022\/05\/2.1.webp\",\"width\":1080,\"height\":600,\"caption\":\"DATUMO\"},\"image\":{\"@id\":\"https:\/\/blog.datumo.com\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/blog.datumo.com\/#\/schema\/person\/02ec2d0ba953b146878dab089dc735b6\",\"name\":\"DATUMO\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/blog.datumo.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/1942a8a63e1c8fa0d9be56cda789edd6c0a866259cd5dca24952597ffa8bab3d?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/1942a8a63e1c8fa0d9be56cda789edd6c0a866259cd5dca24952597ffa8bab3d?s=96&d=mm&r=g\",\"caption\":\"DATUMO\"},\"description\":\"DATUMO, The Data for Smarter AI. We seek to drive impact in the world by providing diverse and high quality data to build smarter AI.\",\"sameAs\":[\"https:\/\/blog.datumo.com\/en\"],\"url\":\"https:\/\/blog.datumo.com\/en\/author\/selectstar\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"The Most Refined Depth Estimation Model: Marigold - DATUMO","description":"Dive into the most refines depth estimation model, Marigold. Marigold, has achieved SOTA results in depth estimation using Stable Diffusion.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/blog.datumo.com\/en\/tech\/16674","og_locale":"ko_KR","og_type":"article","og_title":"The Most Refined Depth Estimation Model: Marigold - DATUMO","og_description":"Dive into the most refines depth estimation model, Marigold. Marigold, has achieved SOTA results in depth estimation using Stable Diffusion.","og_url":"https:\/\/blog.datumo.com\/en\/tech\/16674","og_site_name":"DATUMO","article_published_time":"2024-01-24T04:55:00+00:00","article_modified_time":"2024-10-22T09:06:44+00:00","og_image":[{"width":1920,"height":1440,"url":"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg","type":"image\/jpeg"}],"author":"DATUMO","twitter_card":"summary_large_image","twitter_misc":{"\uae00\uc4f4\uc774":"DATUMO","\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"6\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/blog.datumo.com\/en\/tech\/16674#article","isPartOf":{"@id":"https:\/\/blog.datumo.com\/en\/tech\/16674"},"author":{"name":"DATUMO","@id":"https:\/\/blog.datumo.com\/#\/schema\/person\/02ec2d0ba953b146878dab089dc735b6"},"headline":"The Most Refined Depth Estimation Model: Marigold","datePublished":"2024-01-24T04:55:00+00:00","dateModified":"2024-10-22T09:06:44+00:00","mainEntityOfPage":{"@id":"https:\/\/blog.datumo.com\/en\/tech\/16674"},"wordCount":842,"publisher":{"@id":"https:\/\/blog.datumo.com\/#organization"},"image":{"@id":"https:\/\/blog.datumo.com\/en\/tech\/16674#primaryimage"},"thumbnailUrl":"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg","articleSection":["tech"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/blog.datumo.com\/en\/tech\/16674","url":"https:\/\/blog.datumo.com\/en\/tech\/16674","name":"The Most Refined Depth Estimation Model: Marigold - DATUMO","isPartOf":{"@id":"https:\/\/blog.datumo.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/blog.datumo.com\/en\/tech\/16674#primaryimage"},"image":{"@id":"https:\/\/blog.datumo.com\/en\/tech\/16674#primaryimage"},"thumbnailUrl":"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg","datePublished":"2024-01-24T04:55:00+00:00","dateModified":"2024-10-22T09:06:44+00:00","description":"Dive into the most refines depth estimation model, Marigold. Marigold, has achieved SOTA results in depth estimation using Stable Diffusion.","breadcrumb":{"@id":"https:\/\/blog.datumo.com\/en\/tech\/16674#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/blog.datumo.com\/en\/tech\/16674"]}]},{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/blog.datumo.com\/en\/tech\/16674#primaryimage","url":"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg","contentUrl":"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2024\/01\/milad-fakurian-PGdW_bHDbpI-unsplash.jpg","width":1920,"height":1440},{"@type":"BreadcrumbList","@id":"https:\/\/blog.datumo.com\/en\/tech\/16674#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/blog.datumo.com\/en\/"},{"@type":"ListItem","position":2,"name":"The Most Refined Depth Estimation Model: Marigold"}]},{"@type":"WebSite","@id":"https:\/\/blog.datumo.com\/#website","url":"https:\/\/blog.datumo.com\/","name":"DATUMO","description":"The Data for Smarter AI","publisher":{"@id":"https:\/\/blog.datumo.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/blog.datumo.com\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/blog.datumo.com\/#organization","name":"DATUMO","url":"https:\/\/blog.datumo.com\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/blog.datumo.com\/#\/schema\/logo\/image\/","url":"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2022\/05\/2.1.webp","contentUrl":"https:\/\/blog.datumo.com\/en\/wp-content\/uploads\/2022\/05\/2.1.webp","width":1080,"height":600,"caption":"DATUMO"},"image":{"@id":"https:\/\/blog.datumo.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/blog.datumo.com\/#\/schema\/person\/02ec2d0ba953b146878dab089dc735b6","name":"DATUMO","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/blog.datumo.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/1942a8a63e1c8fa0d9be56cda789edd6c0a866259cd5dca24952597ffa8bab3d?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/1942a8a63e1c8fa0d9be56cda789edd6c0a866259cd5dca24952597ffa8bab3d?s=96&d=mm&r=g","caption":"DATUMO"},"description":"DATUMO, The Data for Smarter AI. We seek to drive impact in the world by providing diverse and high quality data to build smarter AI.","sameAs":["https:\/\/blog.datumo.com\/en"],"url":"https:\/\/blog.datumo.com\/en\/author\/selectstar"}]}},"_links":{"self":[{"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/posts\/16674","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/comments?post=16674"}],"version-history":[{"count":52,"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/posts\/16674\/revisions"}],"predecessor-version":[{"id":16934,"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/posts\/16674\/revisions\/16934"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/media\/16701"}],"wp:attachment":[{"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/media?parent=16674"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/categories?post=16674"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.datumo.com\/en\/wp-json\/wp\/v2\/tags?post=16674"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}