GHOST: Geometry-Guided Hallucination of Opaque Surface Textures

• URL: http://arxiv.org/abs/2607.11118v1
• Date: Mon, 13 Jul 2026 05:50:19 GMT
• Title: GHOST: Geometry-Guided Hallucination of Opaque Surface Textures
• Abstract summary: We propose a novel geometry-guided preprocessing framework to transform transparent regions into opaque, structurally consistent representations.<n>Our method significantly enhances the accuracy of state-of-the-art depth estimation and reconstruction models on transparent objects by restoring essential photometric cues.
• Score: 0.28675177318965045
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transparent objects pose a fundamental challenge for depth estimation and 3D reconstruction due to their violation of Lambertian assumptions, leading to severe geometry degradation in downstream tasks. To address this, we propose a novel geometry-guided preprocessing framework \textbf{GHOST} that leverages visual foundation models to transform transparent regions into opaque, structurally consistent representations without requiring downstream model retraining. Specifically, our pipeline utilizes (1) \textbf{TransDINO} and (2) \textbf{TransDecomp} to disentangle masks and transparency physical properties, while (3) \textbf{DAF-Net} recovers surface normal priors to encode geometric curvature. Subsequently, (4) \textbf{GeoSemTransNet} integrates these multi-modal cues to synthesize a texture-rich opaque RGB image that preserves the transparent object's 3D structure. Extensive experiments demonstrate that our method significantly enhances the accuracy of state-of-the-art depth estimation and reconstruction models on transparent objects by restoring essential photometric cues.

Related papers

• Surfsvr: 2D Surface Priors as 3D Geometric Regularizers for Sparse Voxel Reconstruction [56.51413081953813]
  SurfSVR is a novel sparse voxel reconstruction paradigm that treats 2D surface priors as explicit 3D geometric regularizers.<n>It consistently improves sparse voxel reconstruction across scenes with substantially different visibility and geometry characteristics.
  arXiv  Detail & Related papers  (2026-08-12T11:25:31Z)
• TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction [65.03268438396556]
  TriSplat is a feed-forward reconstruction network that represents scenes with oriented triangle primitives.<n>It exports simulation-ready mesh scenes from a single forward pass.<n>Experiments on RealEstate10K and DL3DV show that this representation produces more geometry-faithful reconstructions than Gaussian feed-forward baselines.
  arXiv  Detail & Related papers  (2026-05-25T17:59:53Z)
• GTSR: Subsurface Scattering Awared 3D Gaussians for Translucent Surface Reconstruction [1.7145735930379027]
  We propose a novel 3DGS-based pipeline (GTSR) to reconstruct the surface geometry of translucent objects.<n>Our method outperforms baseline reconstruction methods on the NeuralTO Syn dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:38:18Z)
• DiffTrans: Differentiable Geometry-Materials Decomposition for Reconstructing Transparent Objects [53.83670041249326]
  Reconstructing transparent objects from a set of multi-view images is a challenging task due to the complicated nature and indeterminate behavior of light propagation.<n>We propose a differentiable rendering framework for transparent objects, dubbed DiffTrans, which allows for efficient decomposition and reconstruction of the geometry and materials of transparent objects.
  arXiv  Detail & Related papers  (2026-02-28T02:21:31Z)
• TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors [39.60777069381983]
  We introduce Transparent Surface Gaussian Splatting (TSGS), a new framework that separates geometry learning from appearance refinement.<n>In the geometry learning stage, TSGS focuses on geometry by using specular-suppressed inputs to accurately represent surfaces.<n>To enhance depth inference, TSGS employs a first-surface depth extraction method.
  arXiv  Detail & Related papers  (2025-04-17T10:00:09Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.<n>Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• Ghost on the Shell: An Expressive Representation of General 3D Shapes [97.76840585617907]
  Meshes are appealing since they enable fast physics-based rendering with realistic material and lighting. Recent work on reconstructing and statistically modeling 3D shapes has critiqued meshes as being topologically inflexible. We parameterize open surfaces by defining a manifold signed distance field on watertight surfaces. G-Shell achieves state-of-the-art performance on non-watertight mesh reconstruction and generation tasks.
  arXiv  Detail & Related papers  (2023-10-23T17:59:52Z)
• Tabletop Transparent Scene Reconstruction via Epipolar-Guided Optical Flow with Monocular Depth Completion Prior [14.049778178534588]
  We introduce a two-stage pipeline for reconstructing transparent objects tailored for mobile platforms. Epipolar-guided Optical Flow (EOF) to fuse several single-view shape priors to a cross-view consistent 3D reconstruction. Our pipeline significantly outperforms baseline methods in 3D reconstruction quality.
  arXiv  Detail & Related papers  (2023-10-15T21:30:06Z)
• NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects [28.62468618676557]
  We propose NEMTO, the first end-to-end neural rendering pipeline to model 3D transparent objects. With 2D images of the transparent object as input, our method is capable of high-quality novel view and relighting synthesis.
  arXiv  Detail & Related papers  (2023-03-21T15:50:08Z)
• Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes [75.63464905190061]
  Complex light paths induced by refraction and reflection have prevented both traditional and deep multiview stereo from solving this problem. We propose a physically-based network to recover 3D shape of transparent objects using a few images acquired with a mobile phone camera. Our experiments show successful recovery of high-quality 3D geometry for complex transparent shapes using as few as 5-12 natural images.
  arXiv  Detail & Related papers  (2020-04-22T23:51:30Z)

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.