<a href=\"https://ut-sysml.github.io/seaotter/\" rel=\"nofollow\">https://ut-sysml.github.io/seaotter/</a></p>\n","updatedAt":"2026-06-05T09:01:21.538Z","author":{"_id":"63213080d2d45f3151837eba","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63213080d2d45f3151837eba/RtN8hNJoMSI5-isnYOyqz.webp","fullname":"Dan Jacobellis","name":"danjacobellis","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":10,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5564404129981995},"editors":["danjacobellis"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/63213080d2d45f3151837eba/RtN8hNJoMSI5-isnYOyqz.webp"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.03940","authors":[{"_id":"6a228ff6047f837f98677877","name":"Dan Jacobellis","hidden":false},{"_id":"6a228ff6047f837f98677878","name":"Neeraja J. Yadwadkar","hidden":false}],"publishedAt":"2026-06-02T00:00:00.000Z","submittedOnDailyAt":"2026-06-05T00:00:00.000Z","title":"SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction","submittedOnDailyBy":{"_id":"63213080d2d45f3151837eba","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63213080d2d45f3151837eba/RtN8hNJoMSI5-isnYOyqz.webp","isPro":true,"fullname":"Dan Jacobellis","user":"danjacobellis","type":"user","name":"danjacobellis"},"summary":"In robotics systems, vast amounts of visual data are easily captured at high resolution using low-cost, low-power hardware. Yet, limited bandwidth and on-device compute resources prevent full utilization when transmitted via conventional codecs like JPEG/MPEG. Newer codecs, like AV1/AVIF, improve the rate-distortion trade-off, but demand far more resources for encoding, impractical without custom ASICs. Recent asymmetric autoencoders deliver high quality under extreme power and bandwidth constraints, but add prohibitive decoding cost and use bespoke formats that ignore decades of infrastructure built around standards like JPEG. To address these limitations, we introduce a compression framework for cloud robotics based on a Sensor Embedded Autoencoder paired with a One-Time Transcode for Efficient Reconstruction (SEAOTTER). Because the sensor, cloud, and consumer stages face very different power and bandwidth budgets, SEAOTTER combines the compactness of a learned latent with the broad usability of a standard JPEG file. Since naive transcoding degrades performance, we propose a learnable JPEG color and quantization transform that enables increased accuracy for global, dense, and vision-language-based perception. Using SEAOTTER, we train both general-purpose and task-aware transcoding pipelines for a pre-trained, frozen encoder. At a compression ratio of 200:1 and compared to AVIF, we observe 7 times faster encoding, 3.5 times faster decoding, and +8% ImageNet top-1 accuracy, while retaining compatibility with JPEG infrastructure. Our code is available at https://github.com/UT-SysML/seaotter .","upvotes":1,"discussionId":"6a228ff7047f837f98677879","projectPage":"https://ut-sysml.github.io/seaotter/","githubRepo":"https://github.com/UT-SysML/seaotter","githubRepoAddedBy":"user","ai_summary":"A compression framework for cloud robotics combines learned latent representations with standard JPEG compatibility to achieve faster encoding and decoding while maintaining high perceptual quality.","ai_keywords":["asymmetric autoencoders","learned latent","JPEG color transform","quantization transform","transcoding","task-aware transcoding","pre-trained encoder","compression ratio","ImageNet top-1 accuracy"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":0},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63213080d2d45f3151837eba","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63213080d2d45f3151837eba/RtN8hNJoMSI5-isnYOyqz.webp","isPro":true,"fullname":"Dan Jacobellis","user":"danjacobellis","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.03940.md"}">
SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction
Abstract
A compression framework for cloud robotics combines learned latent representations with standard JPEG compatibility to achieve faster encoding and decoding while maintaining high perceptual quality.
In robotics systems, vast amounts of visual data are easily captured at high resolution using low-cost, low-power hardware. Yet, limited bandwidth and on-device compute resources prevent full utilization when transmitted via conventional codecs like JPEG/MPEG. Newer codecs, like AV1/AVIF, improve the rate-distortion trade-off, but demand far more resources for encoding, impractical without custom ASICs. Recent asymmetric autoencoders deliver high quality under extreme power and bandwidth constraints, but add prohibitive decoding cost and use bespoke formats that ignore decades of infrastructure built around standards like JPEG. To address these limitations, we introduce a compression framework for cloud robotics based on a Sensor Embedded Autoencoder paired with a One-Time Transcode for Efficient Reconstruction (SEAOTTER). Because the sensor, cloud, and consumer stages face very different power and bandwidth budgets, SEAOTTER combines the compactness of a learned latent with the broad usability of a standard JPEG file. Since naive transcoding degrades performance, we propose a learnable JPEG color and quantization transform that enables increased accuracy for global, dense, and vision-language-based perception. Using SEAOTTER, we train both general-purpose and task-aware transcoding pipelines for a pre-trained, frozen encoder. At a compression ratio of 200:1 and compared to AVIF, we observe 7 times faster encoding, 3.5 times faster decoding, and +8% ImageNet top-1 accuracy, while retaining compatibility with JPEG infrastructure. Our code is available at https://github.com/UT-SysML/seaotter .
Community
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/2606.03940 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.03940 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.03940 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.