[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-metricanything-brings-scaling-laws-to-depth-estimation":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},4168,"metricanything-brings-scaling-laws-to-depth-estimation","MetricAnything Brings Scaling Laws to Depth Estimation","A new open-source framework trains on 20 million noisy image-depth pairs to make metric depth estimation scale like a foundation model.","A research framework called MetricAnything shows that metric depth estimation — pinning exact real-world distances to pixels — can scale the same way large language models do.\n\nThe team trained on roughly 20 million image-depth pairs pulled from reconstructed, captured, and rendered 3D data across 10,000 different camera models. The core trick is a \"Sparse Metric Prompt\": randomly masked depth maps that act as a universal interface, stripping out sensor noise and camera-specific quirks without bespoke engineering for each rig. That lets one model generalize across wildly different hardware instead of being tuned per device. The pretrained model handles depth completion, super-resolution, and radar-camera fusion; a lighter distilled version hits state-of-the-art on monocular depth estimation and multi-view 3D reconstruction.\n\nThe significance is architectural, not just numerical. Depth estimation has historically resisted the scaling playbook because heterogeneous sensors introduce biases that compound at scale — this work argues that a well-designed prompt interface can absorb that noise rather than engineer around it. The researchers also report that plugging the pretrained visual encoder into multimodal large language models improves spatial reasoning, which matters for robotics and vision-language-action planning.\n\nMetricAnything is open-sourced, which puts pressure on proprietary depth pipelines in autonomous vehicles and robotics — though lab benchmarks and real deployment conditions have a habit of diverging in ways that peer review does not catch.","[\"computer-vision\",\"depth-estimation\",\"foundation-models\",\"robotics\"]","2026-07-07T04:00:00.000Z","2026-07-07T18:54:34.200Z","2026-07-07T18:54:37.147Z","published",null,[],"ai",[26,27,28,29],"computer-vision","depth-estimation","foundation-models","robotics",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.22054",0,{"sections":36},[37,41,46,51,56,61,66,71,76,80,85,89,94,99],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":45},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":18},"Dev Tools","dev-tools",59,{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":86,"slug":87,"count":83,"latest_published_at":88},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]