paper-with-me

홈 › Papers

TransCut: Transparent Object Segmentation from a Light-Field Image

2015-11-21 · ICCV 2015 12 · Yichao Xu, Hajime Nagahara, Atsushi Shimada, Rin-ichiro Taniguchi

The segmentation of transparent objects can be very useful in computer vision applications. However, because they borrow texture from their background and have a similar appearance to their surroundings, transparent objects are not handled well by regular image segmentation methods. We propose a method that overcomes these problems using the consistency and distortion properties of a light-field image. Graph-cut optimization is applied for the pixel labeling problem. The light-field linearity is used to estimate the likelihood of a pixel belonging to the transparent object or Lambertian background, and the occlusion detector is used to find the occlusion boundary. We acquire a light field dataset for the transparent object, and use this dataset to evaluate our method. The results demonstrate that the proposed method successfully segments transparent objects from the background.

📄 PDF Abstract BibTeX arXiv:1511.06853

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationObjectSegmentationSemantic SegmentationTransparent objects

Similar Papers 제목 키워드 기반

Deep Polarization Cues for Transparent Object Segmentation

2020-06-01 · CVPR 2020 6 · Agastya Kalra, Vage Taamazyan, Supreeth Krishna Rao, Kartik Venkataraman 외

Segmentation of transparent objects is a hard, open problem in computer vision. Transparent objects lack texture of their own, adopting instead the texture of scene background. This paper reframes the problem of transpar…

Instance SegmentationObjectSegmentationSemantic Segmentation+1

SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objects

2024-03-28 · Avinash Ummadisingu, Jongkeum Choi, Koki Yamane, Shimpei Masuda 외

Acquiring accurate depth information of transparent objects using off-the-shelf RGB-D cameras is a well-known challenge in Computer Vision and Robotics. Depth estimation/completion methods are typically employed and trai…

Depth CompletionDepth EstimationNeRFNovel View Synthesis+2

Segmenting Transparent Object in the Wild with Transformer

2021-01-21 · Enze Xie, Wenjia Wang, Wenhai Wang, Peize Sun 외

This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation dataset. Unlike Trans10K-v1 that only has tw…

DecoderObjectSegmentationSemantic Segmentation+1

LIT: Light-field Inference of Transparency for Refractive Object Localization

2019-10-02 · Zheming Zhou, Xiaotong Chen, Odest Chadwicke Jenkins

Translucency is prevalent in everyday scenes. As such, perception of transparent objects is essential for robots to perform manipulation. Compared with texture-rich or texture-less Lambertian objects, transparency induce…

ObjectObject LocalizationPose EstimationTransparent objects

TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians

2025-04-26 · Letian Huang, Dongwei Ye, Jialin Dan, Chengzhi Tao 외

The emergence of neural and Gaussian-based radiance field methods has led to considerable advancements in novel view synthesis and 3D object reconstruction. Nonetheless, specular reflection and refraction continue to pos…

3D Object ReconstructionInverse RenderingNovel View SynthesisObject Reconstruction+1