mlsanityData to 7 Oct 2026

A Variational U-Net for Conditional Appearance and Shape Generation

arXiv 1804.04694 ↗First posted 12 Apr 2018cs.CVcited by 124

Not on the map. Why?

Abstract (arXiv)

Deep generative models have demonstrated great performance in image synthesis. However, results deteriorate in case of spatial deformations, since they generate images of objects directly, rather than modeling the intricate interplay of their inherent shape and appearance. We present a conditional U-Net for shape-guided image generation, conditioned on the output of a variational autoencoder for appearance. The approach is trained end-to-end on images, without requiring samples of the same object with varying pose or appearance. Experiments show that the model enables conditional image generation and transfer. Therefore, either shape or appearance can be retained from a query image, while freely altering the other. Moreover, appearance can be sampled due to its stochastic latent representation, while preserving shape. In quantitative and qualitative experiments on COCO, DeepFashion, shoes, Market-1501 and handbags, the approach demonstrates significant improvements over the state-of-the-art.

Key facts. Cited by 124 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 59; 2022: 31; 2023: 15; 2024: 11; 2025: 5; 2026: 3.

124 papers.

Sort:

By area:

  1. 2021Neural Articulated Radiance Fieldcited by 196
  2. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 143
  3. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  4. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  5. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 107
  6. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  7. 2022Person Image Synthesis via Denoising Diffusion Modelcited by 104
  8. 2023Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Modelscited by 104
  9. 2022Exploring Dual-task Correlation for Pose Guided Person Image Generationcited by 68
  10. 2022Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representationscited by 65
  11. 2021StylePeople: A Generative Model of Fullbody Human Avatarscited by 62
  12. 2021Neural Re-Rendering of Humans from a Single Imagecited by 59
38 more
  1. 2022Neural Texture Extraction and Distribution for Controllable Person Image Synthesiscited by 55
  2. 2021Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editingcited by 54
  3. 2021Style and Pose Control for Image Synthesis of Humans from a Single Monocular Viewcited by 53
  4. 2022Uncertainty Inspired Underwater Image Enhancementcited by 53
  5. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  6. 2024Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesiscited by 48
  7. 2021HumanGAN: A Generative Model of Humans Imagescited by 47
  8. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  9. 2021Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGANcited by 45
  10. 2022Cross Attention Based Style Distribution for Controllable Person Image Synthesiscited by 45
  11. 2021Learning Semantic Person Image Generation by Region-Adaptive Normalizationcited by 44
  12. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  13. 2021Understanding Object Dynamics for Interactive Image-to-Video Synthesiscited by 38
  14. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  15. 2021Live Speech Portraits: Real-Time Photorealistic Talking-Head Animationcited by 36
  16. 2021ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priorscited by 34
  17. 2021SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detectioncited by 34
  18. 2022HumanGen: Generating Human Radiance Fields with Explicit Priorscited by 33
  19. 2022Text2Human: Text-Driven Controllable Human Image Generationcited by 31
  20. 2025IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layoutcited by 28
  21. 2023A Unified Framework for U-Net Design and Analysiscited by 27
  22. 2024MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinementcited by 24
  23. 2023Learning Data Representations with Joint Diffusion Modelscited by 22
  24. 2021Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modelingcited by 21
  25. 2021Cascaded Cross MLP-Mixer GANs for Cross-View Image Translationcited by 21
  26. 2022Hand-Object Interaction Image Generationcited by 19
  27. 2022Audio-driven Neural Gesture Reenactment with Video Motion Graphscited by 18
  28. 2021CT-Net: Complementary Transfering Network for Garment Transfer with Arbitrary Geometric Changescited by 17
  29. 2021AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Personcited by 17
  30. 2021HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challengecited by 17
  31. 2021AnonySIGN: Novel Human Appearance Synthesis for Sign Language Video Anonymisationcited by 16
  32. 2021Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesiscited by 16
  33. 2021Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistencycited by 15
  34. 2021Behavior-Driven Synthesis of Human Dynamicscited by 14
  35. 2023Human MotionFormer: Transferring Human Motions with Vision Transformerscited by 14
  36. 2022Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Expertscited by 13
  37. 2021Flow Guided Transformable Bottleneck Networks for Motion Retargetingcited by 12
  38. 2021SPG-VTON: Semantic Prediction Guidance for Multi-pose Virtual Try-oncited by 12

50 most cited of 124 All 124 (JSON)