Color Pass-Through aims to make an image captured by a camera and reproduced on a display perceptually match the real scene as viewed through the device. Instead of calibrating the camera and display independently through a predefined intermediate color space, we learn the complete camera-display path end to end for each device.</p>\n<p>In short, Color Pass-Through learns pretrained neural components for a fixed camera-display pair, then uses a one-step calibration for each observer to deliver color pass-through across diverse scenes.</p>\n","updatedAt":"2026-07-24T05:42:10.886Z","author":{"_id":"683971013e5dd928f059bade","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/683971013e5dd928f059bade/0LyqSxoz-cm-JQuIs9ZAx.jpeg","fullname":"Ruikang","name":"Lyricccco","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8787970542907715},"editors":["Lyricccco"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/683971013e5dd928f059bade/0LyqSxoz-cm-JQuIs9ZAx.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.12746","authors":[{"_id":"6a5f07144fe5d1d13e84ac41","user":{"_id":"683971013e5dd928f059bade","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/683971013e5dd928f059bade/0LyqSxoz-cm-JQuIs9ZAx.jpeg","isPro":false,"fullname":"Ruikang","user":"Lyricccco","type":"user","name":"Lyricccco"},"name":"Ruikang Li","status":"claimed_verified","statusLastChangedAt":"2026-07-21T09:32:46.344Z","hidden":false},{"_id":"6a5f07144fe5d1d13e84ac42","name":"Molin Li","hidden":false},{"_id":"6a5f07144fe5d1d13e84ac43","name":"Jiarui Wu","hidden":false},{"_id":"6a5f07144fe5d1d13e84ac44","name":"Zhe Wei","hidden":false},{"_id":"6a5f07144fe5d1d13e84ac45","name":"Pengpeng Liu","hidden":false},{"_id":"6a5f07144fe5d1d13e84ac46","name":"Tianfan Xue","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/683971013e5dd928f059bade/nePVw5wGccvv6PCjK0FSg.webp"],"publishedAt":"2026-07-14T00:00:00.000Z","submittedOnDailyAt":"2026-07-24T00:00:00.000Z","title":"Color Pass-Through via Camera-Display Coupling","submittedOnDailyBy":{"_id":"683971013e5dd928f059bade","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/683971013e5dd928f059bade/0LyqSxoz-cm-JQuIs9ZAx.jpeg","isPro":false,"fullname":"Ruikang","user":"Lyricccco","type":"user","name":"Lyricccco"},"summary":"When a real-world scene is captured by a smartphone camera and viewed on its screen, the displayed image often differs noticeably from the original scene in color, brightness, and contrast. This gap persists despite substantial advances in both modern cameras and displays. A key reason is that most pipelines factor the high-dimensional capture-to-display process into two separately calibrated camera and display stages, and then connect them through low-dimensional color transforms, leading to information bottlenecks and inevitable error accumulation. To address this systemic challenge, we propose Color Pass-Through, an end-to-end learned framework that operates directly on captured images. Our key insight is to treat the camera and display as a coupled system rather than calibrating them in isolation. Coupling the camera and display yields two practical advantages: (1) it brings the entire real-world scenes to the display via end-to-end optimization, and (2) it allows efficient one-step calibration for each distinct observer via complete capture-to-display path. We validate Color Pass-Through using both digital and human observers. Compared with representative baselines, our method achieves an average gain of +2.0 points on a 5-point user study and more than 2x improvement on quantitative metrics, demonstrating improved reproduction of the perceived color of the original scene.","upvotes":17,"discussionId":"6a5f07154fe5d1d13e84ac47","projectPage":"https://lyricccco.github.io/color-pass-through/","githubRepo":"https://github.com/lyricccco/color-pass-through","githubRepoAddedBy":"user","githubStars":38,"organization":{"_id":"6a5f15b1b77765ffe357acea","name":"MMLab-CUHK","fullname":"MMLab-CUHK","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/683971013e5dd928f059bade/BB2gIkNcqFxhcogB5vOiJ.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"683971013e5dd928f059bade","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/683971013e5dd928f059bade/0LyqSxoz-cm-JQuIs9ZAx.jpeg","isPro":false,"fullname":"Ruikang","user":"Lyricccco","type":"user"},{"_id":"67443f7c2f6a94e877c95b32","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/RbMBDBKyHHRjjqn7_t22G.png","isPro":false,"fullname":"Zixuan Chen","user":"zxchen00","type":"user"},{"_id":"659d5f6f499009b2590c0442","avatarUrl":"/avatars/85e3c1d3f10d691b01b0f3085e7dd441.svg","isPro":false,"fullname":"cjeen","user":"cjeen","type":"user"},{"_id":"642c0c2bc01eb0e148ffd57f","avatarUrl":"/avatars/505cf460f2ea5551b4d380ea7810ba5e.svg","isPro":false,"fullname":"Mingde Yao","user":"Mingde","type":"user"},{"_id":"68138bc0fc77e8e3cd176ecb","avatarUrl":"/avatars/4becc5f33fd035fd8c03d7ca9ae1a96d.svg","isPro":false,"fullname":"Jiarui","user":"gnwgnw","type":"user"},{"_id":"65ec2463df813b9c1571da7d","avatarUrl":"/avatars/731c90738d01f4e46dd4503d1a5e5137.svg","isPro":false,"fullname":"yaoruchang","user":"ruchangyao","type":"user"},{"_id":"66743477ab975c859114d410","avatarUrl":"/avatars/ac692cc336e383fb2cb53db6d1e3fe8c.svg","isPro":false,"fullname":"yawenluo","user":"yawenluo","type":"user"},{"_id":"652183c35e7247c2915180a6","avatarUrl":"/avatars/6ef2e6ae496c7226472a61f1cf5718f4.svg","isPro":false,"fullname":"Tianfan","user":"tianfan09","type":"user"},{"_id":"64c8b5f8f3d2a59a431e9e07","avatarUrl":"/avatars/dd489f5178cd28cf2e6c7fbe3df8eb6e.svg","isPro":false,"fullname":"詹佳豪","user":"JohnZhan","type":"user"},{"_id":"69672d93bece445e6907b7a2","avatarUrl":"/avatars/205051944057e7e7a5908c2393f38578.svg","isPro":false,"fullname":"Chen","user":"Yutian10","type":"user"},{"_id":"64c8f16736c11430f31d9bf6","avatarUrl":"/avatars/6907df1fedbcedc63046e7457a6b5950.svg","isPro":false,"fullname":"zhiyuanyou","user":"zhiyuanyou","type":"user"},{"_id":"653cb25c394886efebf9971a","avatarUrl":"/avatars/bca0a20c305e178a3f316581a2636cb6.svg","isPro":false,"fullname":"Xiao Chen","user":"Xiao-HF","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6a5f15b1b77765ffe357acea","name":"MMLab-CUHK","fullname":"MMLab-CUHK","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/683971013e5dd928f059bade/BB2gIkNcqFxhcogB5vOiJ.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.12746.md","query":{}}">
Color Pass-Through via Camera-Display Coupling
Abstract
When a real-world scene is captured by a smartphone camera and viewed on its screen, the displayed image often differs noticeably from the original scene in color, brightness, and contrast. This gap persists despite substantial advances in both modern cameras and displays. A key reason is that most pipelines factor the high-dimensional capture-to-display process into two separately calibrated camera and display stages, and then connect them through low-dimensional color transforms, leading to information bottlenecks and inevitable error accumulation. To address this systemic challenge, we propose Color Pass-Through, an end-to-end learned framework that operates directly on captured images. Our key insight is to treat the camera and display as a coupled system rather than calibrating them in isolation. Coupling the camera and display yields two practical advantages: (1) it brings the entire real-world scenes to the display via end-to-end optimization, and (2) it allows efficient one-step calibration for each distinct observer via complete capture-to-display path. We validate Color Pass-Through using both digital and human observers. Compared with representative baselines, our method achieves an average gain of +2.0 points on a 5-point user study and more than 2x improvement on quantitative metrics, demonstrating improved reproduction of the perceived color of the original scene.
Community
Color Pass-Through aims to make an image captured by a camera and reproduced on a display perceptually match the real scene as viewed through the device. Instead of calibrating the camera and display independently through a predefined intermediate color space, we learn the complete camera-display path end to end for each device.
In short, Color Pass-Through learns pretrained neural components for a fixed camera-display pair, then uses a one-step calibration for each observer to deliver color pass-through across diverse scenes.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2607.12746 in a model README.md to link it from this page.
Cite arxiv.org/abs/2607.12746 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2607.12746 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.