Scal3R Uses Multi-Reference Pose Queries to Cut Drift in Online 3D Reconstruction
Chin-Yang Lin · hf · 2026-09-04
Chin-Yang Lin released Scal3R on Hugging Face, a scalable online 3D reconstruction method for long videos. It queries multi-reference relative poses with lightweight tokens and applies pose-graph optimization to reduce accumulated drift.
Notably, the approach improves long-video reconstruction without retraining the backbone network.
More from Research
- TCR specificity prediction: strong motif in one chain can still be nonbinding with wrong partner — iskander · 2026-09-04
- Purdue's AutoTraceGT automates grounded theory coding to analyze agent behavior at scale — Purdue · 2026-09-04
- Expert explainer on Anthropic's protein binder campaign: design cost cut from $10k to ~$100 — AllThingsApx · 2026-09-04
- Paradigm 3: low-quality RL environments may explain reward hacking; EBR-bench shows humans beat AIs — gleech · 2026-09-04
- Schmidhuber releases report claiming Hinton's Nobel-winning work was plagiarism — SchmidhuberAI · 2026-09-04
- SE-RRM paper hits ARC-AGI with just 2M params amid GPT-6 recurrent depth speculation — gklambauer · 2026-09-04