UniSim-SLAM: feed-forward SLAM with unified Sim(3) optimization lands at ECCV 2026
rsasaki0109 · x · 2026-09-07
Researchers at UNIST (Korea) present UniSim-SLAM (ECCV 2026), a feed-forward SLAM pipeline built on geometric foundation models that runs on phone-captured image sequences:
- Problem: feed-forward predictions depend heavily on the input view set, causing geometric inconsistency and trajectory drift over long sequences; online deployment trades two-view latency against multi-view constraint richness.
- Approach: lightweight two-view keyframe tracking in the frontend plus periodic multi-view submap refinement in the backend, combined in a unified multi-level factor graph on Sim(3) that jointly optimizes global keyframe poses and submap poses despite heterogeneous local scales.
- Key idea: treat two-view and multi-view predictions as complementary constraints—temporal two-view edges preserve tracking connectivity while multi-view submaps provide richer geometric anchors for long-term consistency.
Code is coming soon; a phone-capture demo is available.
More from Embodied
- FLASH: GPU-native deformable sim learns cloth folding in minutes on one RTX 5090 — ChongZzZhang · 2026-10-26
- Luke Wroblewski spots it: iPhone Duo's corner radius mirrors the original iPhone — LukeW · 2026-10-26
- Humanoids shattered forecasts: half-marathon record in 2026, 100m faster than Bolt — ben_j_todd · 2026-10-26
- Humanoid walking is continuous correction — watch recovery, not locomotion, in demos — Olivier__OG · 2026-10-26
- CircuitHub unveils The Grid, a factory-scale robot making PCBs in the US twice as fast as Shenzhen — garrytan · 2026-10-26
- Shanghai AI Lab-led team releases 100-hour egocentric wearable dataset for humanoid training — ChuckDBrooks · 2026-10-26