Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation

• URL: http://arxiv.org/abs/2604.18336v1
• Date: Mon, 20 Apr 2026 14:35:31 GMT
• Title: Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation
• Abstract summary: We propose a training-free framework that leverages depth foundation models as a structural prior.<n>We also introduce tiGlassRecon, a novel RGB-D dataset with geometrically derived ground truth for glass regions.
• Score: 3.49604158786247
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Indoor robot navigation is often compromised by glass surfaces, which severely corrupt depth sensor measurements. While foundation models like Depth Anything 3 provide excellent geometric priors, they lack an absolute metric scale. We propose a training-free framework that leverages depth foundation models as a structural prior, employing a robust local RANSAC-based alignment to fuse it with raw sensor depth. This naturally avoids contamination from erroneous glass measurements and recovers an accurate metric scale. Furthermore, we introduce \ti{GlassRecon}, a novel RGB-D dataset with geometrically derived ground truth for glass regions. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art baselines, especially under severe sensor depth corruption. The dataset and related code will be released at https://github.com/jarvisyjw/GlassRecon.

Related papers

• Glass Surface Detection Grounded in 3D Visual Geometry [118.92003088760919]
  Glass surface detection (GSD) is critical for scene understanding and reconstruction.<n>We propose a paradigm shift: grounding GSD in 3D visual geometry to explicitly model the physical existence of glass surfaces.<n>Our method first distills rich 3D priors from the visual geometry grounded transformer (VGGT) and generates glass-aware 3D representations.
  arXiv  Detail & Related papers  (2026-08-27T07:49:21Z)
• SILICA: Repurposing Diffusion Priors for Joint Glass Segmentation and Depth Estimation [11.131505915750013]
  Standard depth sensors systematically fail on transparent surfaces, creating corrupted 3D maps and navigation hazards.<n>We introduce SILICA, a unified pipeline leveraging text-to-image diffusion models to jointly predict glass segmentation and glass-aware depth.<n> SILICA achieves remarkable zero-shot transfer across diverse, unseen environments, outperforming state-of-the-art models by almost 20%.
  arXiv  Detail & Related papers  (2026-07-27T10:38:49Z)
• AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs [16.622717763906262]
  Currently available depth sensors are prone to errors on transparent, specular, and general non-Lambertian surfaces.<n>We propose a training-free depth grounding framework that anchors monocular depth estimation priors from a depth foundation model.<n>Our method performs a patch-wise affine alignment, locally grounding monocular predictions in metric real-world depth.
  arXiv  Detail & Related papers  (2026-05-04T14:48:52Z)
• In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting [22.674046124865196]
  We introduce a training framework integrating scale-ambiguous and noisy depth priors into geometric supervision.<n>Experiments across diverse datasets show consistent improvements in geometric accuracy.
  arXiv  Detail & Related papers  (2026-04-07T11:15:15Z)
• Robust Depth Enhancement via Polarization Prompt Fusion Tuning [112.88371907047396]
  We present a framework that leverages polarization imaging to improve inaccurate depth measurements from various depth sensors. Our method first adopts a learning-based strategy where a neural network is trained to estimate a dense and complete depth map from polarization data and a sensor depth map from different sensors. To further improve the performance, we propose a Polarization Prompt Fusion Tuning (PPFT) strategy to effectively utilize RGB-based models pre-trained on large-scale datasets.
  arXiv  Detail & Related papers  (2024-04-05T17:55:33Z)
• AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusion [25.32113731681485]
  Underwater perception and 3D surface reconstruction are challenging problems with broad applications in construction, security, marine archaeology, and environmental monitoring. Our work develops a physics-based multimodal acoustic-optical neural surface reconstruction framework. By fusing these complementary modalities, our framework can reconstruct accurate high-resolution 3D surfaces from measurements captured over heavily-restricted baselines.
  arXiv  Detail & Related papers  (2024-02-05T18:59:31Z)
• On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks [61.74608497496841]
  Training on inaccurate or corrupt data induces model bias and hampers generalisation capabilities. This paper investigates the effect of sensor errors for the dense 3D vision tasks of depth estimation and reconstruction.
  arXiv  Detail & Related papers  (2023-03-26T22:32:44Z)
• Leveraging RGB-D Data with Cross-Modal Context Mining for Glass Surface Detection [47.87834602551456]
  Glass surfaces are becoming increasingly ubiquitous as modern buildings tend to use a lot of glass panels.<n>This poses substantial challenges to the operations of autonomous systems such as robots, self-driving cars, and drones.<n>We propose a novel glass surface detection framework combining RGB and depth information.
  arXiv  Detail & Related papers  (2022-06-22T17:56:09Z)
• Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression [34.95597838973912]
  HAMMER is a dataset comprising depth estimates from multiple commonly used sensors for indoor depth estimation. We construct highly reliable ground truth depth maps with the help of 3D scanners and aligned renderings. A popular depth estimators is trained on this data and typical depth senosors.
  arXiv  Detail & Related papers  (2022-05-09T21:25:09Z)
• Mirror3D: Depth Refinement for Mirror Surfaces [15.825231649843332]
  We create the Mirror3D dataset: a 3D mirror plane dataset based on three RGBD datasets. We then develop Mirror3DNet: a module that refines raw sensor depth or estimated depth to correct errors on mirror surfaces. Our experiments show that Mirror3DNet significantly mitigates errors from a variety of input depth data.
  arXiv  Detail & Related papers  (2021-06-11T22:30:12Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)
• 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)

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.