Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

2026-09-03

AI Summary

针对长视频在线3D重建效果差的问题，Scal3R通过多参考相对位姿查询和轻量级学习令牌来优化全局姿态预测，有效减少了累积误差。

Abstract

Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the training distribution. Small drifts accumulate and amplify into significant geometric collapse. However, we observe that per-frame depth remains stable throughout this failure. The backbone's local geometry remains intact; only the global pose head breaks down. Motivated by this decoupling, we introduce Scal3R. This approach reformulates online reconstruction as multi-reference relative pose querying. We use lightweight learnable tokens, which make up about ~1% of the parameters, and inject them into a completely frozen backbone via asymmetric attention. This setup queries poses relative to multiple past keyframes. An online pose-graph optimization system with loop closure suppresses long-range drift. Scal3R reaches convergence in 8 hours on a single GPU. It reduces the average ATE by over 60% on KITTI compared to the online baseline. It also achieves state-of-the-art performance across Virtual KITTI, Sintel, TUM-Dynamic, ScanNet, and 7-Scenes. Project page: https://linjohnss.github.io/scal3r/

Problem

• online 3D reconstruction
• long videos
• pose regression
• geometric collapse
• drift

Innovation

• multi-reference relative pose querying
• lightweight learnable tokens
• asymmetric attention
• online pose-graph optimization