Papers › SCAM! Transferring humans between images with Semantic Cross Attention Modulation

SCAM! Transferring humans between images with Semantic Cross Attention Modulation

10 Oct 2022arXiv:2210.04883archive 2025-07-28

Nicolas Dufour, David Picard, Vicky Kalogeiton

A large body of recent work targets semantically conditioned image generation. Most such methods focus on the narrower task of pose transfer and ignore the more challenging task of subject transfer that consists in not only transferring the pose but also the appearance and background. In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details. This is enabled by the Semantic Attention Transformer Encoder that extracts multiple latent vectors for each semantic region, and the corresponding generator that exploits these multiple latents by using semantic cross attention modulation. It is trained only using a reconstruction setup, while subject transfer is performed at test time. Our analysis shows that our proposed architecture is successful at encoding the diversity of appearance in each semantic region. Extensive experiments on the iDesigner and CelebAMask-HD datasets show that SCAM outperforms SEAN and SPADE; moreover, it sets the new state of the art on subject transfer.

PaperPDFCode

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

Code

nicolas-dufour/SCAM officialmentioned 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

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

Tasks

DiversityImage GenerationPose TransferReconstructionSubject Transfer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Transfer ADE20K SCAM FID 27.5 #1 of 1 Archive leaderboard report
Pose Transfer CelebAMask-HQ SCAM S-FID 19.8 #1 of 1 Archive leaderboard report
Pose Transfer iDesigner SCAM S-FID 26.9 #1 of 1 Archive leaderboard report
Reconstruction ADE20K SCAM PSNR 20 #1 of 1 Archive leaderboard report
Reconstruction CelebAMask-HQ SCAM PSNR 21.9 #1 of 1 Archive leaderboard report
Reconstruction CelebAMask-HQ SCAM R-FID 15.5 #1 of 1 Archive leaderboard report
Reconstruction iDesigner SCAM PSNR 21.4 #1 of 1 Archive leaderboard report
Reconstruction iDesigner SCAM R-FID 13.2 #1 of 1 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 ConnectionSCASoftmaxTestTransformer

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