提出相对回归方法，解决3D重建中全局坐标依赖问题。
$R^3$: 3D Reconstruction via Relative Regression
- 用轻量MLP预测相对约束，避免全局坐标系依赖
- 支持离线全上下文与在线流式重建，内存可控
- 通过置信度加权损失和姿态聚合，提升重建精度
近期的前馈几何基础模型通过单次前向传播恢复深度和位姿，展现出优异的泛化能力。然而，这些模型通常受限于全局坐标系假设，在长序列和流式重建中成为瓶颈，因需维护任意时间原点并处理随时间无界增长的平移量。本文提出R^3，采用相对回归机制：通过轻量MLP预测置信度加权的相对约束，该置信度作为统一锚点，在训练时加权损失，在推理时指导姿态聚合。R^3同时支持全上下文离线重建与因果、有限记忆的流式重建。在离线与流式设置下的评估验证了相对机制的有效性。
原文摘要 · Abstract (English)
Recent feed-forward geometry foundation models have demonstrated impressive generalization by recovering depth and poses in a single forward pass. However, these models are typically constrained by a global coordinate frame assumption. This dependency becomes a significant bottleneck for long-context and streaming reconstruction, as it forces the network to maintain an arbitrary temporal origin and handle translation magnitudes that grow unbounded over time. Our solution, which we call $R^3$, employs relative regression. We employ a lightweight MLP to predict confidence-weighted relative constraints. These confidences serve as a unified anchor: weighting losses during training and guiding pose aggregation during inference. $R^3$ supports both full-context offline reconstruction and causal, bounded-memory streaming. Our evaluation in both offline and streaming settings validates the effectiveness of our relative mechanism. Project page: https://kevinxu02.github.io/r3-site
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。