mlsanityData to 14 Oct 2026

Multi-focal Conditioned Latent Diffusion for Person Image Synthesis

arXiv 2503.15686 ↗First posted 19 Mar 2025cs.CVcited by 6

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

Abstract (arXiv)

The Latent Diffusion Model (LDM) has demonstrated strong capabilities in high-resolution image generation and has been widely employed for Pose-Guided Person Image Synthesis (PGPIS), yielding promising results. However, the compression process of LDM often results in the deterioration of details, particularly in sensitive areas such as facial features and clothing textures. In this paper, we propose a Multi-focal Conditioned Latent Diffusion (MCLD) method to address these limitations by conditioning the model on disentangled, pose-invariant features from these sensitive regions. Our approach utilizes a multi-focal condition aggregation module, which effectively integrates facial identity and texture-specific information, enhancing the model's ability to produce appearance realistic and identity-consistent images. Our method demonstrates consistent identity and appearance generation on the DeepFashion dataset and enables flexible person image editing due to its generation consistency. The code is available at https://github.com/jqliu09/mcld.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 47 of its 58 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

47 of 58 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis28 Feb
  2. 2023StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On4 Dec
  3. 2023HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation2 Oct
  4. 2023UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer18 Apr
  5. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  6. 2022Person Image Synthesis via Denoising Diffusion Model22 Nov
  7. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 40

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  11. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  12. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
28 more
  1. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  2. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 688
  3. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  4. 2024InstantID: Zero-shot Identity-Preserving Generation in Secondscited by 436
  5. 2022Blended Latent Diffusioncited by 432
  6. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  7. 2024Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidancecited by 272
  8. 2017Pose Guided Person Image Generationcited by 251
  9. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  10. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  11. 2020Controllable Person Image Synthesis with Attribute-Decomposed GANcited by 150
  12. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 144
  13. 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
  14. 2019DwNet: Dense warp-based network for pose-guided human video generationcited by 115
  15. 2023TADA! Text to Animatable Digital Avatarscited by 110
  16. 2019Dense Intrinsic Appearance Flow for Human Pose Transfercited by 104
  17. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
  18. 2020Deep Image Spatial Transformation for Person Image Generationcited by 100
  19. 2021PISE: Person Image Synthesis and Editing with Decoupled GANcited by 62
  20. 2021Neural Re-Rendering of Humans from a Single Imagecited by 59
  21. 2022Neural Texture Extraction and Distribution for Controllable Person Image Synthesiscited by 55
  22. 2021Style and Pose Control for Image Synthesis of Humans from a Single Monocular Viewcited by 53
  23. 2022Cross Attention Based Style Distribution for Controllable Person Image Synthesiscited by 45
  24. 2021Learning Semantic Person Image Generation by Region-Adaptive Normalizationcited by 44
  25. 2020Bipartite Graph Reasoning GANs for Person Image Generationcited by 34
  26. 2019Appearance and Pose-Conditioned Human Image Generation using Deformable GANscited by 24
  27. 2021Flow Guided Transformable Bottleneck Networks for Motion Retargetingcited by 12
  28. 2021Combining Attention with Flow for Person Image Synthesiscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfercited by 9
  2. 2026OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generationcited by 2
  3. 2026DAC-Pose: Dual-Agent Collaborative Framework for Pose-Guided Human Generationcited by 1
  4. 2025Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesiscited by 0
  5. 2025Pro-Pose: Unpaired Full-Body Portrait Synthesis via Canonical UV Mapscited by 0
  6. 2026PHAC: Promptable Human Amodal Completioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
  2. 2025TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer
  3. 2024DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images
  4. 2024Cross-view Masked Diffusion Transformers for Person Image Synthesis
  5. 2026One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model
  6. 2026Identity-Conditioned Latent Consistency Distillation for Face Synthesis
  7. 2024Fusion Embedding for Pose-Guided Person Image Synthesis with Diffusion Model
  8. 2024Multimodal-Conditioned Latent Diffusion Models for Fashion Image Editing