SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification

• URL: http://arxiv.org/abs/2603.19547v1
• Date: Fri, 20 Mar 2026 01:08:04 GMT
• Title: SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification
• Abstract summary: SeeClear is a novel framework that converts transparent objects into generative opaque images.<n>It enables stable monocular depth estimation for transparent objects.<n> Experiments on both synthetic and real-world datasets show that SeeClear significantly improves depth estimation for transparent objects.
• Score: 21.13173486320481
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Monocular depth estimation remains challenging for transparent objects, where refraction and transmission are difficult to model and break the appearance assumptions used by depth networks. As a result, state-of-the-art estimators often produce unstable or incorrect depth predictions for transparent materials. We propose SeeClear, a novel framework that converts transparent objects into generative opaque images, enabling stable monocular depth estimation for transparent objects. Given an input image, we first localize transparent regions and transform their refractive appearance into geometrically consistent opaque shapes using a diffusion-based generative opacification module. The processed image is then fed into an off-the-shelf monocular depth estimator without retraining or architectural changes. To train the opacification model, we construct SeeClear-396k, a synthetic dataset containing 396k paired transparent-opaque renderings. Experiments on both synthetic and real-world datasets show that SeeClear significantly improves depth estimation for transparent objects. Project page: https://heyumeng.com/SeeClear-web/

Related papers

• Trans2Occ: Voxel Occupancy Estimation and Grasp for Transparent Objects from Simulation to Reality [125.76063573012853]
  We present a framework for transparent object perception and manipulation based on single-view RGB input.<n>Our approach predicts voxel-space occupancy directly from a single image, providing a geometry-aware representation that supports downstream robotic grasping.
  arXiv  Detail & Related papers  (2026-06-01T06:59:13Z)
• RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives [52.10688811929143]
  We propose a unified framework that integrates a microfacet material model and ray tracing to jointly model specular reflection and transmittance in Gaussian Splatting.<n>Our experiments demonstrate that our method successfully produces reflections and recovers objects behind transparent surfaces in complex environments.
  arXiv  Detail & Related papers  (2026-04-01T05:50:03Z)
• Transparent Fragments Contour Estimation via Visual-Tactile Fusion for Autonomous Reassembly [69.97596838714595]
  We propose a general transparent fragments contour estimation framework based on visual-tactile fusion.<n>By fusing tactile information with visual cues, a visual-tactile fusion material is proposed.<n> experimental results demonstrate the validity of the proposed framework.
  arXiv  Detail & Related papers  (2026-03-18T14:58:17Z)
• 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)
• Fix False Transparency by Noise Guided Splatting [4.778060896816705]
  Opaque objects reconstructed by 3DGS often exhibit a falsely transparent surface.<n>This issue stems from the ill-posed optimization in 3DGS.<n>We propose a strategy to encourage surface Gaussians to adopt higher opacity.
  arXiv  Detail & Related papers  (2025-10-17T15:28:24Z)
• ReFlow6D: Refraction-Guided Transparent Object 6D Pose Estimation via Intermediate Representation Learning [48.29147383536012]
  We present ReFlow6D, a novel method for transparent object 6D pose estimation.<n>Unlike conventional approaches, our method leverages a feature space impervious to changes in RGB image space and independent of depth information.<n>We show that ReFlow6D achieves precise 6D pose estimation of transparent objects, using only RGB images as input.
  arXiv  Detail & Related papers  (2024-12-30T09:53:26Z)
• From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS [41.38491898098891]
  This paper introduces $alpha$-Neus -- an extension of NeuS -- that proves NeuS is unbiased for materials from fully transparent to fully opaque.<n>We develop a method to extract the transparent and opaque surface simultaneously based onDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes.
  arXiv  Detail & Related papers  (2024-11-08T06:36:31Z)
• RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation [50.10282876199739]
  This paper introduces RFTrans, an RGB-D-based method for surface normal estimation and manipulation of transparent objects. It integrates the RFNet, which predicts refractive flow, object mask, and boundaries, followed by the F2Net, which estimates surface normal from the refractive flow. A real-world robot grasping task witnesses an 83% success rate, proving that refractive flow can help enable direct sim-to-real transfer.
  arXiv  Detail & Related papers  (2023-11-21T07:19:47Z)
• TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation [6.844391823478345]
  We propose a two-stage pipeline that estimates category-level transparent object pose using localized depth completion and surface normal estimation. Results show that TransNet achieves improved pose estimation accuracy on transparent objects. We use TransNet to build an autonomous transparent object manipulation system for robotic pick-and-place and pouring tasks.
  arXiv  Detail & Related papers  (2023-07-23T18:38:42Z)
• StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS [106.62225866064313]
  We present StereoPose, a novel stereo image framework for category-level object pose estimation. For a robust estimation from pure stereo images, we develop a pipeline that decouples category-level pose estimation into object size estimation, initial pose estimation, and pose refinement. To address the issue of image content aliasing, we define a back-view NOCS map for the transparent object. The back-view NOCS aims to reduce the network learning ambiguity caused by content aliasing, and leverage informative cues on the back of the transparent object for more accurate pose estimation.
  arXiv  Detail & Related papers  (2022-11-03T08:36:09Z)
• TODE-Trans: Transparent Object Depth Estimation with Transformer [16.928131778902564]
  We present a transformer-based transparent object depth estimation approach from a single RGB-D input. To better enhance the fine-grained features, a feature fusion module (FFM) is designed to assist coherent prediction.
  arXiv  Detail & Related papers  (2022-09-18T03:04:01Z)
• TransNet: Category-Level Transparent Object Pose Estimation [6.844391823478345]
  The lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. A second challenge is that common depth sensors typically used for opaque object perception cannot obtain accurate depth measurements on transparent objects. We propose TransNet, a two-stage pipeline that learns to estimate category-level transparent object pose using localized depth completion and surface normal estimation.
  arXiv  Detail & Related papers  (2022-08-22T01:34:31Z)
• TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and Grasping [46.6058840385155]
  We contribute a large-scale real-world dataset for transparent object depth completion. Our dataset contains 57,715 RGB-D images from 130 different scenes. We propose an end-to-end depth completion network, which takes the RGB image and the inaccurate depth map as inputs and outputs a refined depth map.
  arXiv  Detail & Related papers  (2022-02-17T06:50:20Z)
• 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.