ECCV 2026 to host full-day workshop on 3D vision in the era of world models
songyoupeng · x · 2026-09-08
ECCV 2026 will host "3D in the Era of World Models," a full-day workshop on September 9 in Malmö exploring how explicit 3D structure, spatial intelligence, and video generation fit into scalable world models. Key topics: when explicit 3D representations are necessary, whether video pretraining yields spatially grounded understanding, 4D long-context modeling, evaluation beyond pixel fidelity, and robotics applications. Non-archival paper submissions are open.
Related event: ECCV 2026 to Host Full-Day Workshop on 3D in the Era of World Models(3 posts)→
More from Research
- Stu-tU: RANSAC scoring that survives 128x scale miscalibration — ducha_aiki · 2026-09-09
- Test-time compute could be 10,000 model instances coordinating on a message board — mertdumenci · 2026-09-09
- Do transformers lose object-like 'seeing' of definitions through training? — MoonL88537 · 2026-09-09
- Marigold V2 retools diffusion transformers for sharper monocular depth estimation — huawei-bayerlab · 2026-09-09
- kornia-rs: Rust Low-Level 3D Vision Library Outperforms OpenCV and NVIDIA VPI — edgarriba · 2026-09-09
- Researcher cites more blogposts and HF links than papers, blames academia — antoine_chaffin · 2026-09-09