Papers › SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human...

SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction

10 Dec 2023CVPR 2024 1arXiv:2312.06704archive 2025-07-28

Zechuan Zhang, Zongxin Yang, Yi Yang

Creating high-quality 3D models of clothed humans from single images for real-world applications is crucial. Despite recent advancements, accurately reconstructing humans in complex poses or with loose clothing from in-the-wild images, along with predicting textures for unseen areas, remains a significant challenge. A key limitation of previous methods is their insufficient prior guidance in transitioning from 2D to 3D and in texture prediction. In response, we introduce SIFU (Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction), a novel approach combining a Side-view Decoupling Transformer with a 3D Consistent Texture Refinement pipeline.SIFU employs a cross-attention mechanism within the transformer, using SMPL-X normals as queries to effectively decouple side-view features in the process of mapping 2D features to 3D. This method not only improves the precision of the 3D models but also their robustness, especially when SMPL-X estimates are not perfect. Our texture refinement process leverages text-to-image diffusion-based prior to generate realistic and consistent textures for invisible views. Through extensive experiments, SIFU surpasses SOTA methods in both geometry and texture reconstruction, showcasing enhanced robustness in complex scenarios and achieving an unprecedented Chamfer and P2S measurement. Our approach extends to practical applications such as 3D printing and scene building, demonstrating its broad utility in real-world scenarios. Project page https://river-zhang.github.io/SIFU-projectpage/ .

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="2312.06704")

Code

Syntology Ran 13 of 18 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: official repository: 18 samples from 1 repository, 13 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/SIFU officialmentioned on GitHubpytorchMIT 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; 13 ran; 0 honoured the contract we drafted; 5 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.

13ran
5unverified

Licence: 0 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/SIFU. “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.

build_smooth_conv3D River-Zhang/SIFU/lib/common/seg3d_utils.py official repository ran MIT (permissive) · c25753fc9d52f1fc · report
create_grid2D River-Zhang/SIFU/lib/common/seg3d_utils.py official repository ran MIT (permissive) · c07f0db88d9cd069 · report
create_grid3D River-Zhang/SIFU/lib/common/seg3d_utils.py official repository ran MIT (permissive) · 8e3d9f38a1b40efc · report
gen_mesh_color River-Zhang/SIFU/apps/infer.py official repository ran MIT (permissive) · 3771ef371f90d296 · report
gen_mesh_eval River-Zhang/SIFU/lib/common/train_util.py official repository ran MIT (permissive) · 8f032be442a1aef5 · report
load_calib River-Zhang/SIFU/apps/infer.py official repository ran MIT (permissive) · e23beb1e7eafd0a8 · report
load_segmentation River-Zhang/SIFU/lib/common/cloth_extraction.py official repository ran MIT (permissive) · 3433ad17bc7e6650 · report
parse_args River-Zhang/SIFU/lib/common/config.py official repository ran MIT (permissive) · 27cd0667887a625b · report
rename River-Zhang/SIFU/lib/common/train_util.py official repository ran MIT (permissive) · 66fb5ef9d96ef0a8 · report
solid_angles River-Zhang/SIFU/lib/common/render_utils.py official repository ran MIT (permissive) · bd32d6f5d82a5a9e · report
transform_to_tensor River-Zhang/SIFU/lib/common/imutils.py official repository ran MIT (permissive) · 31b960f8590428bd · report
vertex_colors_to_texture River-Zhang/SIFU/apps/infer.py official repository ran MIT (permissive) · b8a4086cbd7b040e · report
winding_numbers River-Zhang/SIFU/lib/common/render_utils.py official repository ran MIT (permissive) · cd54a895a2ab8720 · report
get_affine_matrix_box River-Zhang/SIFU/lib/common/imutils.py official repository unverified MIT (permissive) · 227a4974e3e6917b · report
get_affine_matrix_wh River-Zhang/SIFU/lib/common/imutils.py official repository unverified MIT (permissive) · 00f9feda347a4ad9 · report
reshape_sample_tensor River-Zhang/SIFU/lib/common/train_util.py official repository unverified MIT (permissive) · 79509ef34e0af8e4 · report
smpl_to_recon_labels River-Zhang/SIFU/lib/common/cloth_extraction.py official repository unverified MIT (permissive) · 32b523249d5d7868 · report
update_cfg River-Zhang/SIFU/lib/common/config.py official repository unverified MIT (permissive) · 938f7173c2e6ab9c · report

Tasks

Lifelike 3D Human Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lifelike 3D Human Generation THuman2.0 Dataset SIFU CLIP Similarity 0.8663 #5 of 6 Archive leaderboard report
Lifelike 3D Human Generation THuman2.0 Dataset SIFU LPIPS 0.1500 #5 of 6 Archive leaderboard report
Lifelike 3D Human Generation THuman2.0 Dataset SIFU PSNR 16.4600 #5 of 6 Archive leaderboard report
Lifelike 3D Human Generation THuman2.0 Dataset SIFU SSIM 0.7931 #5 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

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

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