$R^3$: 3D Reconstruction via Relative Regression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910270647959552 |
|---|---|
| author | Xu, Congrong Gao, Huachen Chen, Xingyu Xiu, Yuliang Gao, Jun Chen, Anpei |
| author_facet | Xu, Congrong Gao, Huachen Chen, Xingyu Xiu, Yuliang Gao, Jun Chen, Anpei |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26519 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | $R^3$: 3D Reconstruction via Relative Regression Xu, Congrong Gao, Huachen Chen, Xingyu Xiu, Yuliang Gao, Jun Chen, Anpei Computer Vision and Pattern Recognition 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 |
| title | $R^3$: 3D Reconstruction via Relative Regression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.26519 |