Papers › Pose Guided Person Image Generation

Pose Guided Person Image Generation

25 May 2017NeurIPS 2017 12arXiv:1705.09368archive 2025-07-28

Liqian Ma, Xu Jia, Qianru Sun, Bernt Schiele, Tinne Tuytelaars, Luc van Gool

This paper proposes the novel Pose Guided Person Generation Network (PG²) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose. Our generation framework PG² utilizes the pose information explicitly and consists of two key stages: pose integration and image refinement. In the first stage the condition image and the target pose are fed into a U-Net-like network to generate an initial but coarse image of the person with the target pose. The second stage then refines the initial and blurry result by training a U-Net-like generator in an adversarial way. Extensive experimental results on both 128×64 re-identification images and 256×256 fashion photos show that our model generates high-quality person images with convincing details.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

chuanqichen/deepcoaching mentioned on GitHubpytorchSyntology: not harvested report
sgoldyaev/DeepFashion.ADGAN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Controllable Person Image Synthesis with Attribute-Decomposed GAN (arXiv:2003.12267; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Gesture-to-Gesture TranslationImage GenerationPose Transfer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Gesture-to-Gesture Translation NTU Hand Digit PG2 AMT 3.5 #4 of 6 Archive leaderboard report
Gesture-to-Gesture Translation NTU Hand Digit PG2 IS 2.4152 #4 of 6 Archive leaderboard report
Gesture-to-Gesture Translation NTU Hand Digit PG2 PSNR 28.2403 #4 of 6 Archive leaderboard report
Gesture-to-Gesture Translation Senz3D PG2 AMT 2.8 #3 of 6 Archive leaderboard report
Gesture-to-Gesture Translation Senz3D PG2 IS 3.3699 #3 of 6 Archive leaderboard report
Gesture-to-Gesture Translation Senz3D PG2 PSNR 26.5138 #3 of 6 Archive leaderboard report
Pose Transfer Deep-Fashion PG Squared IS 3.090 #8 of 12 Archive leaderboard report
Pose Transfer Deep-Fashion PG Squared SSIM 0.762 #8 of 12 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