paper-with-me

Papers

TetraTSDF: 3D human reconstruction from a single image with a tetrahedral outer shell

2020-04-22 · CVPR 2020 6 · Hayato Onizuka, Zehra Hayirci, Diego Thomas, Akihiro Sugimoto, Hideaki Uchiyama, Rin-ichiro Taniguchi

Recovering the 3D shape of a person from its 2D appearance is ill-posed due to ambiguities. Nevertheless, with the help of convolutional neural networks (CNN) and prior knowledge on the 3D human body, it is possible to overcome such ambiguities to recover detailed 3D shapes of human bodies from single images. Current solutions, however, fail to reconstruct all the details of a person wearing loose clothes. This is because of either (a) huge memory requirement that cannot be maintained even on modern GPUs or (b) the compact 3D representation that cannot encode all the details. In this paper, we propose the tetrahedral outer shell volumetric truncated signed distance function (TetraTSDF) model for the human body, and its corresponding part connection network (PCN) for 3D human body shape regression. Our proposed model is compact, dense, accurate, and yet well suited for CNN-based regression task. Our proposed PCN allows us to learn the distribution of the TSDF in the tetrahedral volume from a single image in an end-to-end manner. Results show that our proposed method allows to reconstruct detailed shapes of humans wearing loose clothes from single RGB images.

📄 PDF Abstract BibTeX arXiv:2004.10534

Code (1)

diegothomas/TetraTSDF 공식 구현 tf

Tasks

3D Human Reconstructionregression

Similar Papers 제목 키워드 기반

Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Maps

2023-11-27 · Jane Wu, Diego Thomas, Ronald Fedkiw

We present a novel deep learning-based approach to the 3D reconstruction of clothed humans using weak supervision via 2D normal maps. Given a single RGB image or multiview images, our network infers a signed distance fun…

3D Reconstruction

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

2020-11-03 · NeurIPS 2020 12 · Jun Gao, Wenzheng Chen, Tommy Xiang, Clement Fuji Tsang 외

3D shape representations that accommodate learning-based 3D reconstruction are an open problem in machine learning and computer graphics. Previous work on neural 3D reconstruction demonstrated benefits, but also limitati…

3D Reconstruction

HoloTetSphere: Unified TetSphere Mesh Reconstruction for Physical Simulations

2026-07-09 · YaQiao Dai, Renjiao Yi, Zhirui Gao, Wei Chen 외 arxiv

Standard pipelines for physics-ready 3D reconstruction rely on a decoupled two-stage paradigm: extracting surface geometry followed by an error-prone tetrahedralization process. While recent Lagrangian methods like TetSp…

Physical Simulations3D Reconstruction

TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

2024-05-30 · Minghao Guo, Bohan Wang, Kaiming He, Wojciech Matusik

We introduce TetSphere Splatting, a Lagrangian geometry representation designed for high-quality 3D shape modeling. TetSphere splatting leverages an underused yet powerful geometric primitive -- volumetric tetrahedral me…

3D Generation3D Reconstruction3D Shape ModelingComputational Efficiency+4

HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained Images

2023-11-27 · CVPR 2024 1 · Xihe Yang, Xingyu Chen, Daiheng Gao, Shaohui Wang 외

As for human avatar reconstruction, contemporary techniques commonly necessitate the acquisition of costly data and struggle to achieve satisfactory results from a small number of casual images. In this paper, we investi…