paper-with-me

홈 › Papers

Refining 3D Human Texture Estimation from a Single Image

2023-03-06 · Said Fahri Altindis, Adil Meric, Yusuf Dalva, Ugur Gudukbay, Aysegul Dundar

Estimating 3D human texture from a single image is essential in graphics and vision. It requires learning a mapping function from input images of humans with diverse poses into the parametric (UV) space and reasonably hallucinating invisible parts. To achieve a high-quality 3D human texture estimation, we propose a framework that adaptively samples the input by a deformable convolution where offsets are learned via a deep neural network. Additionally, we describe a novel cycle consistency loss that improves view generalization. We further propose to train our framework with an uncertainty-based pixel-level image reconstruction loss, which enhances color fidelity. We compare our method against the state-of-the-art approaches and show significant qualitative and quantitative improvements.

📄 PDF Abstract BibTeX arXiv:2303.03471

Code (1)

saidaltindis/refinetex 공식 구현

Tasks

Image Reconstruction

Methods 이 논문이 사용한 방법론

Deformable Convolution Deformable convolutions add 2D offsets to the regular grid sampling locations in the standard convolution. It enables free…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Cycle Consistency Loss Cycle Consistency Loss is a type of loss used for generative adversarial networks that performs unpaired image-to-image translation. It was introduced with the…

Similar Papers 제목 키워드 기반

Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks

2023-05-01 · Sihun Cha, Kwanggyoon Seo, Amirsaman Ashtari, Junyong Noh

There has been significant progress in generating an animatable 3D human avatar from a single image. However, recovering texture for the 3D human avatar from a single image has been relatively less addressed. Because the…

Texture Synthesis

GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

2024-11-27 · Wentao Wang, Hang Ye, Fangzhou Hong, Xue Yang 외

Given a single in-the-wild human photo, it remains a challenging task to reconstruct a high-fidelity 3D human model. Existing methods face difficulties including a) the varying body proportions captured by in-the-wild hu…

3D Human ReconstructionImage to 3D

3D Human Texture Estimation from a Single Image with Transformers

2021-09-06 · ICCV 2021 10 · Xiangyu Xu, Chen Change Loy

We propose a Transformer-based framework for 3D human texture estimation from a single image. The proposed Transformer is able to effectively exploit the global information of the input image, overcoming the limitations …

Garment Reconstruction

SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Image

2023-09-04 · Dan Casas, Marc Comino-Trinidad

We propose SMPLitex, a method for estimating and manipulating the complete 3D appearance of humans captured from a single image. SMPLitex builds upon the recently proposed generative models for 2D images, and extends the…

Re-Identification Supervised Texture Generation

2019-04-06 · CVPR 2019 6 · Jian Wang, Yunshan Zhong, Yachun Li, Chi Zhang 외

The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years. However, the texture generation problem has not been fully discussed. In this paper, we propose an end-to-e…

Person Re-IdentificationTexture Synthesis