computer-vision-8

Garment Reconstruction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in garment-reconstruction-8

Trend

Dataset

Best Model

Actions

4D-DRESS

Libraries

i

Use these libraries to find garment-reconstruction-8 models and implementations

Datasets

4D-DRESS

GarmentCodeData

Subtasks

No subtasks available.

Most implemented papers

Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images

Xiaoguang Han, Shuguang Cui, Heming Zhu, Yu Cao, Hang Jin, Weikai Chen, Dong Du, Zhangye Wang•Fri Mar 27 2020

Deep Fashion3D is introduced, the largest collection to date of 3D garment models, with the goal of establishing a novel benchmark and dataset for the evaluation of image-based garment reconstruction systems.

166

Content

0

Paper Graph

Towards Garment Sewing Pattern Reconstruction from a Single Image

Shuicheng Yan, Lijuan Liu, Xiangyu Xu, Zhijie Lin, Jiabin Liang•Mon Nov 06 2023

This work synthesizes a versatile dataset, named SewFactory, which consists of around 1M images and ground-truth sewing patterns for model training and quantitative evaluation, and proposes a two-level Transformer network called Sewformer, which significantly improves the sewing pattern prediction performance.

43 0

Paper Graph

SMPLicit: Topology-aware Generative Model for Clothed People

F. Moreno-Noguer, Gerard Pons-Moll, Albert Pumarola, Enric Corona, G. Alenyà•Wed Mar 10 2021

SMPLicit is introduced, a novel generative model to jointly represent body pose, shape and clothing geometry that can represent in a unified manner different garment topologies while controlling other properties like the garment size or tightness/looseness.

214 0

Paper Graph

BCNet: Learning Body and Cloth Shape from A Single Image

H. Bao, Juyong Zhang, Ligang Liu, Boyi Jiang, Yang Hong, Jinhao Luo•Tue Mar 31 2020

This paper proposes a layered garment representation on top of SMPL and novelly makes the skinning weight of garment independent of the body mesh, which significantly improves the expression ability of the garment model.

190 0

Paper Graph

Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction

Ling Shao, Shengcai Liao, Fang Zhao, Wenhao Wang•Wed Aug 18 2021

AnchorUDF represents 3D shapes by predicting unsigned distance fields (UDFs) to enable open garment surface modeling at arbitrary resolution and achieves the state-of-the-art performance on single-view garment reconstruction.

62 0

Paper Graph

3D Human Texture Estimation from a Single Image with Transformers

Chen Change Loy•Sun Sep 05 2021

A Transformer-based framework for 3D human texture estimation from a single image is proposed, able to effectively exploit the global information of the input image, overcoming the limitations of existing methods that are solely based on convolutional neural networks.

44 0

Paper Graph

3D Clothed Human Reconstruction in the Wild

Kyoung Mu Lee, Gyeongsik Moon, Takaaki Shiratori, Hyeongjin Nam•Tue Jul 19 2022

ClothWild is proposed, a 3D clothed human reconstruction framework that firstly addresses the robustness on in-the-wild images, and designs a DensePose-based loss function to reduce ambiguities of the weak supervision.

56 0

Paper Graph

Garment4D: Garment Reconstruction from Point Cloud Sequences

Ziwei Liu, Liang Pan, Zhongang Cai, Fangzhou Hong•Tue Dec 07 2021

A principled framework that uses 3D point cloud sequences of dressed humans for garment reconstruction, and introduces a novel Proposal-Guided Hierarchical Feature Network and Iterative Graph Convolution Network, which integrate both high-level semantic features and low-level geometric features for fine details reconstruction.

30 0

Paper Graph

REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos

Mutian Xu, Xiaoguang Han, Guanying Chen, Lingteng Qiu, Jiapeng Zhou, Junle Wang•Mon May 22 2023

This paper introduces a novel approach, called REC-MV, to jointly optimize the explicit feature curves and the implicit signed distance field (SDF) of the garments, so that the open garment meshes can be extracted via garment template registration in the canonical space.

38 0

Paper Graph

DIG: Draping Implicit Garment over the Human Body

P. Fua, Ren Li, Benoît Guillard, Edoardo Remelli•Wed Sep 21 2022

An end-to-end differentiable pipeline is proposed that represents garments using implicit surfaces and learns a skinning field conditioned on shape and pose parameters of an articulated body model that allows to recover body and garments parameters jointly from image observations, something that previous work could not do.

25 0

Paper Graph

Adding a benchmark result helps the community track progress.