| title | SurGe: Improved Surface Geometry in Point Maps |
|---|---|
| authors | Karim Knaebel, Gonzalo Martin Garcia, Christian Schmidt, Ilya Fradlin, Lucas Nunes, Daan de Geus, Bastian Leibe |
| date | 2026-05-29 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.31577 |
| affiliation | RWTH Computer Vision Group |
| upvotes | 6 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Recent feedforward 3D reconstruction methods predict point maps and estimate global 3D geometry remarkably well. However, their predictions still exhibit inaccurate local surface geometry, which is clearly visible qualitatively but only weakly reflected in common metrics. To make these errors more explicit in evaluation, we introduce a point map normal metric that evaluates the local surface orientation induced by neighboring 3D predictions. To reduce these errors, we propose two complementary components: a point gradient matching loss that supervises depth-normalized 3D finite differences, and a Neighborhood Attention Decoder (NAD) that progressively upsamples features and uses Neighborhood Attention for local feature mixing. Across eight zero-shot monocular geometry benchmarks, our model, SurGe, achieves the best average rank for global point map AbsRel and consistently improves local point map and point map normal evaluations. |
cite
@misc{knaebel2026surge,
title={SurGe: Improved Surface Geometry in Point Maps},
author={Karim Knaebel and Gonzalo Martin Garcia and Christian Schmidt and Ilya Fradlin and Lucas Nunes and Daan de Geus and Bastian Leibe},
year={2026},
eprint={2605.31577},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.31577}
}