mlsanityData to 14 Oct 2026

View Synthesis by Appearance Flow

arXiv 1605.03557 ↗First posted 11 May 2016cs.CVcited by 172

Not on the map. Why?

Abstract (arXiv)

We address the problem of novel view synthesis: given an input image, synthesizing new images of the same object or scene observed from arbitrary viewpoints. We approach this as a learning task but, critically, instead of learning to synthesize pixels from scratch, we learn to copy them from the input image. Our approach exploits the observation that the visual appearance of different views of the same instance is highly correlated, and such correlation could be explicitly learned by training a convolutional neural network (CNN) to predict appearance flows -- 2-D coordinate vectors specifying which pixels in the input view could be used to reconstruct the target view. Furthermore, the proposed framework easily generalizes to multiple input views by learning how to optimally combine single-view predictions. We show that for both objects and scenes, our approach is able to synthesize novel views of higher perceptual quality than previous CNN-based techniques.

Key facts. Cited by 172 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 51; 2022: 37; 2023: 33; 2024: 27; 2025: 18; 2026: 6.

172 papers.

Sort:

By area:

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  3. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 343
  4. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  5. 2024A Survey on 3D Gaussian Splattingcited by 224
  6. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  7. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  8. 2021Neural Articulated Radiance Fieldcited by 196
  9. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  10. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 182
  11. 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 180
  12. 2023StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-Oncited by 175
38 more
  1. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  2. 2021Parser-Free Virtual Try-on via Distilling Appearance Flowscited by 143
  3. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  4. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  5. 2023CompGS: Smaller and Faster Gaussian Splatting with Vector Quantizationcited by 130
  6. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 121
  7. 2023GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learningcited by 120
  8. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  9. 2022IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolationcited by 109
  10. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 100
  11. 2022Style-Based Global Appearance Flow for Virtual Try-Oncited by 88
  12. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  13. 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
  14. 2021GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Drivingcited by 75
  15. 2022Single Stage Virtual Try-on via Deformable Attention Flowscited by 65
  16. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  17. 2024Advances in 3D Generation: A Surveycited by 63
  18. 2021GAN-Supervised Dense Visual Alignmentcited by 62
  19. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  20. 2022Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulationcited by 57
  21. 2021CDFI: Compression-Driven Network Design for Frame Interpolationcited by 56
  22. 2022Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Imagecited by 55
  23. 2023A Dynamic Multi-Scale Voxel Flow Network for Video Predictioncited by 53
  24. 2021Free-viewpoint Indoor Neural Relighting from Multi-view Stereocited by 50
  25. 2024Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-Oncited by 38
  26. 2021ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priorscited by 35
  27. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  28. 2024TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Renderingcited by 33
  29. 2023DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Viewscited by 31
  30. 2021Fast and Explicit Neural View Synthesiscited by 28
  31. 2022Cross-View Panorama Image Synthesiscited by 26
  32. 2024MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinementcited by 24
  33. 2021Tracking People with 3D Representationscited by 22
  34. 2022Hardly Perceptible Trojan Attack against Neural Networks with Bit Flipscited by 22
  35. 2024GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Promptingcited by 22
  36. 2021Cascaded Cross MLP-Mixer GANs for Cross-View Image Translationcited by 21
  37. 2021Cross-View Exocentric to Egocentric Video Synthesiscited by 20
  38. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 20

50 most cited of 172 All 172 (JSON)