Papers › Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

24 Sep 2023NeurIPS 2023 11arXiv:2309.13524archive 2025-07-28

Zechuan Zhang, Li Sun, Zongxin Yang, Ling Chen, Yi Yang

Reconstructing 3D clothed human avatars from single images is a challenging task, especially when encountering complex poses and loose clothing. Current methods exhibit limitations in performance, largely attributable to their dependence on insufficient 2D image features and inconsistent query methods. Owing to this, we present the Global-correlated 3D-decoupling Transformer for clothed Avatar reconstruction (GTA), a novel transformer-based architecture that reconstructs clothed human avatars from monocular images. Our approach leverages transformer architectures by utilizing a Vision Transformer model as an encoder for capturing global-correlated image features. Subsequently, our innovative 3D-decoupling decoder employs cross-attention to decouple tri-plane features, using learnable embeddings as queries for cross-plane generation. To effectively enhance feature fusion with the tri-plane 3D feature and human body prior, we propose a hybrid prior fusion strategy combining spatial and prior-enhanced queries, leveraging the benefits of spatial localization and human body prior knowledge. Comprehensive experiments on CAPE and THuman2.0 datasets illustrate that our method outperforms state-of-the-art approaches in both geometry and texture reconstruction, exhibiting high robustness to challenging poses and loose clothing, and producing higher-resolution textures. Codes will be available at https://github.com/River-Zhang/GTA.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2309.13524")

Code

Syntology Ran 15 of 18 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 14 ran with no contract checked.

By repository: official repository: 18 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

river-zhang/gta officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested; 15 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
14ran
3unverified

Licence: 18 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from river-zhang/gta. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Attention river-zhang/gta/lib/net/Transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · d47a4cbea53360d1 · report
CrossAttention river-zhang/gta/lib/net/Transformer.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · c770dc5d61e03875 · report
CrossTransformer river-zhang/gta/lib/net/Transformer.py official repository ran no licence file found · pointer only · 16245abf3ac1d730 · report
FeedForward river-zhang/gta/lib/net/Transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · 3059b2cea63f72e8 · report
PreNorm river-zhang/gta/lib/net/Transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · ae274a9ba388ad5f · report
build_smooth_conv3D River-Zhang/GTA/lib/common/seg3d_utils.py official repository ran no licence file found · pointer only · c25753fc9d52f1fc · report
create_grid2D River-Zhang/GTA/lib/common/seg3d_utils.py official repository ran no licence file found · pointer only · c07f0db88d9cd069 · report
create_grid3D River-Zhang/GTA/lib/common/seg3d_utils.py official repository ran no licence file found · pointer only · 8e3d9f38a1b40efc · report
gen_mesh_color river-zhang/gta/apps/infer.py official repository ran · our draft was wrong no licence file found · pointer only · 0ac51880d133df40 · report
gen_mesh_eval River-Zhang/GTA/lib/common/train_util.py official repository ran no licence file found · pointer only · 8f032be442a1aef5 · report
load_segmentation River-Zhang/GTA/lib/common/cloth_extraction.py official repository ran no licence file found · pointer only · 3433ad17bc7e6650 · report
parse_args River-Zhang/GTA/lib/common/config.py official repository ran no licence file found · pointer only · 27cd0667887a625b · report
rename River-Zhang/GTA/lib/common/train_util.py official repository ran no licence file found · pointer only · 66fb5ef9d96ef0a8 · report
solid_angles River-Zhang/GTA/lib/common/render_utils.py official repository ran no licence file found · pointer only · bd32d6f5d82a5a9e · report
winding_numbers River-Zhang/GTA/lib/common/render_utils.py official repository ran no licence file found · pointer only · cd54a895a2ab8720 · report
reshape_sample_tensor River-Zhang/GTA/lib/common/train_util.py official repository unverified no licence file found · pointer only · 79509ef34e0af8e4 · report
smpl_to_recon_labels River-Zhang/GTA/lib/common/cloth_extraction.py official repository unverified no licence file found · pointer only · 32b523249d5d7868 · report
update_cfg River-Zhang/GTA/lib/common/config.py official repository unverified no licence file found · pointer only · 938f7173c2e6ab9c · report

Tasks

Decoder

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections