Info3R: information-adaptive test-time training cuts KITTI pose error 1.68x vs LongStream
zhenjun_zhao · x · 2026-09-22
Info3R introduces information-aware state updates modulated by each frame's redundancy and a dynamic state reset triggered by cumulative update magnitude and prediction confidence. It consistently improves pose estimation, video depth and 3D reconstruction, with 1.68x lower ATE than LongStream on KITTI Odometry.
More from Embodied
- Snap Specs' $2,195 Launch Faces 'Creep Glasses' Backlash and Apple's $1,999 Foldable iPhone — adariostrange · 2026-09-22
- Huawei MateBook Fold review: a 1.16kg 13-inch notebook that unfolds into an 18-inch 3.3K OLED, ~$3,700, China-only — anthara_ai · 2026-09-22
- Gemini beats GPT-6 Astra at robot capture the flag, winning 70% of matches — chris_j_paxton · 2026-09-22
- Meta Ray-Ban glasses talking to Muse could become the best consumer AI app overnight — ChrisUniverse · 2026-09-22
- JHU to host Scalable Tactile Sensing for Dexterous Manipulation workshop at IROS 2026 — _krishna_murthy · 2026-09-22
- SLIM-init: line-feature VIO initialization for degenerate motions, accepted to IROS 2026 — zhenjun_zhao · 2026-09-22