SurGe: Improved Surface Geometry in Point Maps

• URL: http://arxiv.org/abs/2605.31577v1
• Date: Fri, 29 May 2026 17:46:46 GMT
• Title: SurGe: Improved Surface Geometry in Point Maps
• Abstract summary: feedforward 3D reconstruction methods predict point maps and estimate global 3D geometry remarkably well.<n>Their predictions still exhibit inaccurate local surface geometry, which is clearly visible qualitatively but only weakly reflected in common metrics.<n>We introduce a point map normal metric that evaluates the local surface orientation induced by neighboring 3D predictions.<n>Our model, SurGe, achieves the best average rank for global point map AbsRel and consistently improves local point map and point map normal evaluations.
• Score: 16.32758571104305
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Improving Map Consistency in Graph-Based LiDAR SLAM Through Information-Aware Odometry and Retroactive Loop Closure [22.762295959731233]
  We address the problem of improving global trajectory estimation and local map quality in 3D LiDAR SLAM.<n>We first propose a framework to efficiently estimate geometry-dependent information matrices for ICP, enabling principled weighting of odometry constraints in a pose graph.<n>We then introduce a hierarchical loop-closure module that decouples place recognition from geometric registration, together with a retroactive loop-closure module that exploits the optimized pose graph to recover missed loop closures.
  arXiv  Detail & Related papers  (2026-07-15T07:12:14Z)
• GGPT: Geometry Grounded Point Transformer [22.64445696362087]
  We introduce the Geometry-Grounded Point Transformer (GGPT), a framework that augments feed-forward reconstruction with reliable sparse geometric guidance.<n>Building on this foundation, we propose a geometry-guided 3D point transformer that refines dense point maps under explicit partial-geometry supervision.
  arXiv  Detail & Related papers  (2026-03-11T18:00:04Z)
• Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction [2.760653393100493]
  3D Gaussian Splatting (3DGS) achieves remarkable results in the field of surface reconstruction.<n>However, when Gaussian normal vectors are aligned within the single-view projection plane, while the geometry appears reasonable in the current view, biases may emerge upon switching to nearby views.<n>We develop a multi-view normal enhancement module, which ensures consistency across views by matching the normals of pixel points in nearby views and calculating the loss.
  arXiv  Detail & Related papers  (2025-08-11T07:25:13Z)
• Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting [57.43483622778394]
  We introduce PM-Loss, a novel regularization loss based on a pointmap predicted by a pre-trained transformer.<n>With the improved depth map, our method significantly improves the feed-forward 3DGS across various architectures and scenes.
  arXiv  Detail & Related papers  (2025-06-05T17:58:23Z)
• OffsetOPT: Explicit Surface Reconstruction without Normals [7.297352404640493]
  We propose OffsetOPT, a method that reconstructs explicit surfaces directly from 3D point clouds.<n>We demonstrate its accuracy on popular benchmarks, including small-scale shapes and large-scale open surfaces.
  arXiv  Detail & Related papers  (2025-03-20T00:47:27Z)
• Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation [39.79759035338819]
  We present two basic design principles to bridge the gap between estimated and precise surface normals. We implement these two principles using deep neural networks, and integrate them with the state-of-the-art (SOTA) normal estimation methods in a plug-and-play manner.
  arXiv  Detail & Related papers  (2023-03-30T05:59:43Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• Soft Expectation and Deep Maximization for Image Feature Detection [68.8204255655161]
  We propose SEDM, an iterative semi-supervised learning process that flips the question and first looks for repeatable 3D points, then trains a detector to localize them in image space. Our results show that this new model trained using SEDM is able to better localize the underlying 3D points in a scene.
  arXiv  Detail & Related papers  (2021-04-21T00:35:32Z)
• GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation [204.13451624763735]
  We propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. GeoNet++ effectively predicts depth and surface normals with strong 3D consistency and sharp boundaries. In contrast to current metrics that focus on evaluating pixel-wise error/accuracy, 3DGM measures whether the predicted depth can reconstruct high-quality 3D surface normals.
  arXiv  Detail & Related papers  (2020-12-13T06:48:01Z)
• Better Patch Stitching for Parametric Surface Reconstruction [100.55842629739574]
  We introduce an approach that explicitly encourages global consistency of the local mappings. The first term exploits the surface normals and requires that they remain locally consistent when estimated within and across the individual mappings. The second term further encourages better spatial configuration of the mappings by minimizing novel stitching error.
  arXiv  Detail & Related papers  (2020-10-14T12:37:57Z)
• Occlusion-Aware Depth Estimation with Adaptive Normal Constraints [85.44842683936471]
  We present a new learning-based method for multi-frame depth estimation from a color video. Our method outperforms the state-of-the-art in terms of depth estimation accuracy.
  arXiv  Detail & Related papers  (2020-04-02T07:10:45Z)
• ASLFeat: Learning Local Features of Accurate Shape and Localization [42.70030492742363]
  We present ASLFeat, with three light-weight yet effective modifications to mitigate above issues. First, we resort to deformable convolutional networks to densely estimate and apply local transformation. Second, we take advantage of the inherent feature hierarchy to restore spatial resolution and low-level details for accurate keypoint localization.
  arXiv  Detail & Related papers  (2020-03-23T04:03:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.