Scal3R (ECCV 2026): online 3D reconstruction collapses on long videos due to global pose head
CMHungSteven · x · 2026-09-07
New ECCV 2026 paper Scal3R investigates why online 3D reconstruction models collapse on long videos even when per-frame depth remains stable. The authors find local geometry is often still reliable; it's the global pose head that breaks, and propose a fix accordingly.
More from Research
- Proto-tools, a universal infrastructure layer for generative biology, now open source — jmschreiber91 · 2026-10-26
- New paper finds AI agents negotiate badly under uncertainty and break deals on purpose — xuanalogue · 2026-10-26
- MCP fault injection study: agent task scores drop 60% under realistic tool failures, scale doesn't help — dair_ai · 2026-10-26
- Study: AI reviewing AI misses most reward hacking; best models miss 25%+ of hacks — ronbodkin · 2026-10-26
- FLUX.3 Klein step-distilled to 4-8 steps with CFG baked in — Fit-Structure-6489 · 2026-10-26
- NLI alone rejects 5/6 new agent memories; a 0.45 similarity gate fixes it all — Alternative_Pin9598 · 2026-10-26