VidMap: ETH researchers open-source video-based Structure-from-Motion system at ECCV 2026
RexDouglass · x · 2026-09-07
Researchers (Zador Pataki, Paul-Edouard Sarlin, Marc Pollefeys) present VidMap at ECCV 2026, an offline Structure-from-Motion system for video that combines temporal tracks, loop closures, metric depth, and global optimization to estimate camera poses, intrinsics, and a sparse 3D map. The code is open-sourced on GitHub (410 stars), with a poster (#157) and a ViLMa workshop talk at the conference.
More from Research
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27
- Artificial Analysis breaks down all sub-evaluations in Intelligence Index v4.3.2 — ArtificialAnlys · 2026-10-27
- Infini-AI Lab open-sources Hermit, a framework for agent harness evolution and continual learning — BeidiChen · 2026-10-27
- Meta FAIR's Self-Direction turns agent failures into reusable LoRA skills, +13.8pp on Terminal-Bench — karen_ullrich · 2026-10-27
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Why don't more LLMs ship 10M-token context? A researcher asks about attention tradeoffs — agarwl_ · 2026-10-27