mlsanityData to 7 Oct 2026

Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesis

arXiv 2511.15092 ↗First posted 19 Nov 2025cs.CVcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Pose-guided human image generation is limited by incomplete textures from single reference views and the absence of explicit cross-view interaction. We present jointly conditioned diffusion model (JCDM), a jointly conditioned diffusion framework that exploits multi-view priors. The appearance prior module (APM) infers a holistic identity preserving prior from incomplete references, and the joint conditional injection (JCI) mechanism fuses multi-view cues and injects shared conditioning into the denoising backbone to align identity, color, and texture across poses. JCDM supports a variable number of reference views and integrates with standard diffusion backbones with minimal and targeted architectural modifications. Experiments demonstrate state of the art fidelity and cross-view consistency.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 17 of its 23 references that are in the map. First posted on arXiv 19 Nov 2025.

Builds on

17 of 23 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Multi-focal Conditioned Latent Diffusion for Person Image Synthesis19 Mar
  2. 2024GRPose: Learning Graph Relations for Human Image Generation with Pose Priors29 Aug
  3. 2024Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis28 Feb
  4. 2023Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models10 Oct
  5. 2022Person Image Synthesis via Denoising Diffusion Model22 Nov

Other references · 12

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  4. 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 307
  5. 2017Pose Guided Person Image Generationcited by 251
  6. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  7. 2020Controllable Person Image Synthesis with Attribute-Decomposed GANcited by 150
  8. 2020Deep Image Spatial Transformation for Person Image Generationcited by 100
  9. 2022Exploring Dual-task Correlation for Pose Guided Person Image Generationcited by 68
  10. 2022Neural Texture Extraction and Distribution for Controllable Person Image Synthesiscited by 55
  11. 2022Cross Attention Based Style Distribution for Controllable Person Image Synthesiscited by 45
  12. 2024Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generationcited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model
  2. 2024Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Prior
  3. 2024Cross-view Masked Diffusion Transformers for Person Image Synthesis
  4. 2025HumanGif: Single-View Human Diffusion with Generative Prior
  5. 2023DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis
  6. 2024Consistent Human Image and Video Generation with Spatially Conditioned Diffusion
  7. 2025SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation
  8. 2022Novel View Synthesis with Diffusion Models