Papers › PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

13 May 2019ICCV 2019 10arXiv:1905.05172archive 2025-07-28

Shunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima, Angjoo Kanazawa, Hao Li

We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object. Using PIFu, we propose an end-to-end deep learning method for digitizing highly detailed clothed humans that can infer both 3D surface and texture from a single image, and optionally, multiple input images. Highly intricate shapes, such as hairstyles, clothing, as well as their variations and deformations can be digitized in a unified way. Compared to existing representations used for 3D deep learning, PIFu can produce high-resolution surfaces including largely unseen regions such as the back of a person. In particular, it is memory efficient unlike the voxel representation, can handle arbitrary topology, and the resulting surface is spatially aligned with the input image. Furthermore, while previous techniques are designed to process either a single image or multiple views, PIFu extends naturally to arbitrary number of views. We demonstrate high-resolution and robust reconstructions on real world images from the DeepFashion dataset, which contains a variety of challenging clothing types. Our method achieves state-of-the-art performance on a public benchmark and outperforms the prior work for clothed human digitization from a single image.

PaperPDFConference PDFCode

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

Code

shunsukesaito/PIFu mentioned on GitHubpytorchNOASSERTION 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Human Pose Estimation3D Human Reconstruction3D Object Reconstruction3D Object Reconstruction From A Single Image3D Shape Reconstruction3D Shape Reconstruction From A Single 2D ImageLifelike 3D Human GenerationVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Reconstruction 4D-DRESS PIFu_Inner Chamfer (cm) 2.696 #15 of 22 Archive leaderboard report
3D Human Reconstruction 4D-DRESS PIFu_Inner IoU 0.690 #15 of 22 Archive leaderboard report
3D Human Reconstruction 4D-DRESS PIFu_Inner Normal Consistency 0.792 #15 of 22 Archive leaderboard report
3D Human Reconstruction 4D-DRESS PIFu_Outer Chamfer (cm) 2.783 #16 of 22 Archive leaderboard report
3D Human Reconstruction 4D-DRESS PIFu_Outer IoU 0.697 #16 of 22 Archive leaderboard report
3D Human Reconstruction 4D-DRESS PIFu_Outer Normal Consistency 0.759 #16 of 22 Archive leaderboard report
3D Human Reconstruction CAPE PIFu (THuman2.0) Chamfer (cm) 3.573 #4 of 4 Archive leaderboard report
3D Human Reconstruction CAPE PIFu (THuman2.0) NC 0.186 #4 of 4 Archive leaderboard report
3D Human Reconstruction CAPE PIFu (THuman2.0) P2S (cm) 1.483 #4 of 4 Archive leaderboard report
3D Human Reconstruction CustomHumans PIFu Chamfer Distance P-to-S 2.209 #5 of 8 Archive leaderboard report
3D Human Reconstruction CustomHumans PIFu Chamfer Distance S-to-P 2.582 #5 of 8 Archive leaderboard report
3D Human Reconstruction CustomHumans PIFu Normal Consistency 0.805 #5 of 8 Archive leaderboard report
3D Human Reconstruction CustomHumans PIFu f-Score 34.881 #5 of 8 Archive leaderboard report
3D Object Reconstruction RenderPeople PIFu (3 views) Chamfer (cm) 0.567 #1 of 1 Archive leaderboard report
3D Object Reconstruction RenderPeople PIFu (3 views) Point-to-surface distance (cm) 0.554 #1 of 1 Archive leaderboard report
3D Object Reconstruction RenderPeople PIFu (3 views) Surface normal consistency 0.094 #1 of 1 Archive leaderboard report
3D Object Reconstruction From A Single Image BUFF PIFu Chamfer (cm) 1.14 #4 of 5 Archive leaderboard report
3D Object Reconstruction From A Single Image BUFF PIFu Point-to-surface distance (cm) 1.15 #4 of 5 Archive leaderboard report
3D Object Reconstruction From A Single Image BUFF PIFu Surface normal consistency 0.0928 #4 of 5 Archive leaderboard report
3D Object Reconstruction From A Single Image RenderPeople PIFu Chamfer (cm) 1.5 #2 of 4 Archive leaderboard report
3D Object Reconstruction From A Single Image RenderPeople PIFu Point-to-surface distance (cm) 1.52 #2 of 4 Archive leaderboard report
3D Object Reconstruction From A Single Image RenderPeople PIFu Surface normal consistency 0.084 #2 of 4 Archive leaderboard report
Lifelike 3D Human Generation THuman2.0 Dataset PIFu CLIP Similarity 0.8501 #6 of 6 Archive leaderboard report
Lifelike 3D Human Generation THuman2.0 Dataset PIFu LPIPS 0.1615 #6 of 6 Archive leaderboard report
Lifelike 3D Human Generation THuman2.0 Dataset PIFu PSNR 15.0248 #6 of 6 Archive leaderboard report
Lifelike 3D Human Generation THuman2.0 Dataset PIFu SSIM 0.8884 #6 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.

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