Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
- 类型：arxiv
- 标识：2609.04201
- 链接：https://arxiv.org/abs/2609.04201
- 主分类：engineering
- 形态：method
- TLDR：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
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-04-agent-rag-longcontext-candidates.json