paper-with-me

Papers

Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completion

2019-04-17 · Tao Hu, Zhizhong Han, Abhinav Shrivastava, Matthias Zwicker

We propose a novel approach for 3D shape completion by synthesizing multi-view depth maps. While previous work for shape completion relies on volumetric representations, meshes, or point clouds, we propose to use multi-view depth maps from a set of fixed viewing angles as our shape representation. This allows us to be free of the limitations of memory for volumetric representations and point clouds by casting shape completion into an image-to-image translation problem. Specifically, we render depth maps of the incomplete shape from a fixed set of viewpoints, and perform depth map completion in each view. Different from image-to-image translation network that completes each view separately, our novel network, multi-view completion net (MVCN), leverages information from all views of a 3D shape to help the completion of each single view. This enables MVCN to leverage more information from different depth views to achieve high accuracy in single depth view completion and keep the consistency among the completed depth images in different views. Benefited by the multi-view representation and the novel network structure, MVCN significantly improves the accuracy of 3D shape completion in large-scale benchmarks compared to the state of the art.

📄 PDF Abstract BibTeX arXiv:1904.08366

Code (0)

등록된 구현이 없습니다.

Tasks

Image-to-Image TranslationTranslation

Similar Papers 제목 키워드 기반

Enhancing Neural Radiance Fields with Depth and Normal Completion Priors from Sparse Views

2024-07-08 · Jiawei Guo, HungChyun Chou, Ning Ding

Neural Radiance Fields (NeRF) are an advanced technology that creates highly realistic images by learning about scenes through a neural network model. However, NeRF often encounters issues when there are not enough image…

NeRFPatch Matching

Sparse Pose Trajectory Completion

2021-05-01 · Bo Liu, Mandar Dixit, Roland Kwitt, Gang Hua 외

We propose a method to learn, even using a dataset where objects appear only in sparsely sampled views (e.g. Pix3D), the ability to synthesize a pose trajectory for an arbitrary reference image. This is achieved with a c…

Novel View SynthesisObject

Learning Robust Image-Based Rendering on Sparse Scene Geometry via Depth Completion

2022-01-01 · CVPR 2022 1 · Yuqi Sun, Shili Zhou, Ri Cheng, Weimin Tan 외

Recent image-based rendering (IBR) methods usually adopt plenty of views to reconstruct dense scene geometry. However, the number of available views is limited in practice. When only few views are provided, the perfo…

Depth Completion

3D Shape Generation and Completion through Point-Voxel Diffusion

2021-04-08 · ICCV 2021 10 · Linqi Zhou, Yilun Du, Jiajun Wu

We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike most existing models that learn to deterministically translate a latent vector to a shape, our model, Point-Voxel Diffusion (PVD), is…

3D Shape GenerationDenoising

Deep Depth Completion of a Single RGB-D Image

2018-03-25 · CVPR 2018 6 · Yinda Zhang, Thomas Funkhouser

The goal of our work is to complete the depth channel of an RGB-D image. Commodity-grade depth cameras often fail to sense depth for shiny, bright, transparent, and distant surfaces. To address this problem, we train a d…

Depth CompletionDepth Estimation