mlsanityData to 14 Oct 2026

Learning to Stylize Novel Views

arXiv 2105.13509 ↗First posted 27 May 2021cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

We tackle a 3D scene stylization problem - generating stylized images of a scene from arbitrary novel views given a set of images of the same scene and a reference image of the desired style as inputs. Direct solution of combining novel view synthesis and stylization approaches lead to results that are blurry or not consistent across different views. We propose a point cloud-based method for consistent 3D scene stylization. First, we construct the point cloud by back-projecting the image features to the 3D space. Second, we develop point cloud aggregation modules to gather the style information of the 3D scene, and then modulate the features in the point cloud with a linear transformation matrix. Finally, we project the transformed features to 2D space to obtain the novel views. Experimental results on two diverse datasets of real-world scenes validate that our method generates consistent stylized novel view synthesis results against other alternative approaches.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). Builds on 86 of its 117 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

86 of 117 references.

References · 86

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  8. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  10. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  11. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  12. 2020Neural Sparse Voxel Fieldscited by 959
38 more
  1. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  2. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  3. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  4. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  5. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  6. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  7. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  8. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  9. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  10. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  11. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  12. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  13. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  14. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  15. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  16. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  17. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  18. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 467
  19. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 449
  20. 2017Neural 3D Mesh Renderercited by 437
  21. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 415
  22. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  23. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  24. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  25. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  26. 2017Universal Style Transfer via Feature Transformscited by 354
  27. 2019Neural Point-Based Graphicscited by 327
  28. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  29. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  30. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  31. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  32. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  33. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
  34. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  35. 2020Free View Synthesiscited by 231
  36. 2021Editing Conditional Radiance Fieldscited by 222
  37. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 216
  38. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 8; 2023: 19; 2024: 28; 2025: 11; 2026: 8.

76 papers.

Sort:

By area:

  1. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  2. 2023GaussianEditor: Editing 3D Gaussians Delicately with Text Instructionscited by 168
  3. 2022ARF: Artistic Radiance Fieldscited by 147
  4. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  5. 2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
  6. 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 94
  7. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
  8. 2024StyleGaussian: Instant 3D Style Transfer with Gaussian Splattingcited by 79
  9. 2024ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fieldscited by 68
  10. 2022Unified Implicit Neural Stylizationcited by 67
  11. 2024Advances in 3D Generation: A Surveycited by 63
  12. 2021StyleMesh: Style Transfer for Indoor 3D Scene Reconstructionscited by 58
38 more
  1. 2022UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scenecited by 47
  2. 20213D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Imagecited by 45
  3. 2022Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylizationcited by 35
  4. 2022SNeRF: Stylized Neural Implicit Representations for 3D Scenescited by 26
  5. 2024StylizedGS: Controllable Stylization for 3D Gaussian Splattingcited by 23
  6. 2023Super-NeRF: View-consistent Detail Generation for NeRF super-resolutioncited by 21
  7. 2023Locally Stylized Neural Radiance Fieldscited by 20
  8. 2024Chat-Edit-3D: Interactive 3D Scene Editing via Text Promptscited by 19
  9. 2023ProteusNeRF: Fast Lightweight NeRF Editing using 3D-Aware Image Contextcited by 17
  10. 2023Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Modelscited by 16
  11. 2024Geometry Transfer for Stylizing Radiance Fieldscited by 16
  12. 2024Gaussian Splatting in Stylecited by 16
  13. 2024Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3Dcited by 15
  14. 2023Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylizationcited by 14
  15. 2024Reference-based Controllable Scene Stylization with Gaussian Splattingcited by 12
  16. 2024NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFscited by 11
  17. 2024InstantStyleGaussian: Efficient Art Style Transfer with 3D Gaussian Splattingcited by 11
  18. 2024TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent Editingcited by 10
  19. 2023Creative Birds: Self-Supervised Single-View 3D Style Transfercited by 9
  20. 2023Editing 3D Scenes via Text Prompts without Retrainingcited by 8
  21. 2023Advances in 3D Neural Stylization: A Surveycited by 8
  22. 2025ABC-GS: Alignment-Based Controllable Style Transfer for 3D Gaussian Splattingcited by 7
  23. 2023ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylizationcited by 6
  24. 2025StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussianscited by 6
  25. 2023LAENeRF: Local Appearance Editing for Neural Radiance Fieldscited by 5
  26. 2024ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fieldscited by 5
  27. 2024Freditor: High-Fidelity and Transferable NeRF Editing by Frequency Decompositioncited by 5
  28. 2024DATENeRF: Depth-Aware Text-based Editing of NeRFscited by 5
  29. 2024G-Style: Stylized Gaussian Splattingcited by 5
  30. 2026PEGAsus: 3D Personalization of Geometry and Appearancecited by 5
  31. 2023AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptationcited by 4
  32. 20243DStyleGLIP: Part-Tailored Text-Guided 3D Neural Stylizationcited by 4
  33. 2024ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylizationcited by 4
  34. 2025Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Stylescited by 4
  35. 2025Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Stylescited by 4
  36. 20263DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editingcited by 4
  37. 2023Instant Photorealistic Neural Radiance Fields Stylizationcited by 3
  38. 2023S2RF: Semantically Stylized Radiance Fieldscited by 3

50 most cited of 76 All 76 (JSON)