mlsanityData to 14 Oct 2026

3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image

arXiv 2112.00169 ↗First posted 30 Nov 2021cs.CV cs.GRcited by 45

Not on the map. Why?

Abstract (arXiv)

Visual content creation has spurred a soaring interest given its applications in mobile photography and AR / VR. Style transfer and single-image 3D photography as two representative tasks have so far evolved independently. In this paper, we make a connection between the two, and address the challenging task of 3D photo stylization - generating stylized novel views from a single image given an arbitrary style. Our key intuition is that style transfer and view synthesis have to be jointly modeled for this task. To this end, we propose a deep model that learns geometry-aware content features for stylization from a point cloud representation of the scene, resulting in high-quality stylized images that are consistent across views. Further, we introduce a novel training protocol to enable the learning using only 2D images. We demonstrate the superiority of our method via extensive qualitative and quantitative studies, and showcase key applications of our method in light of the growing demand for 3D content creation from 2D image assets.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Builds on 47 of its 62 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

47 of 62 references.

References · 47

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  10. 2021Vision Transformers for Dense Predictioncited by 1,803
  11. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  12. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
35 more
  1. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  2. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  3. 2015A Neural Algorithm of Artistic Stylecited by 483
  4. 2019PointRend: Image Segmentation as Renderingcited by 440
  5. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  6. 2017Universal Style Transfer via Feature Transformscited by 354
  7. 2016A Learned Representation For Artistic Stylecited by 341
  8. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  9. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  10. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  11. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 198
  12. 2021AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfercited by 178
  13. 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 174
  14. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  15. 20193D Ken Burns Effect from a Single Imagecited by 128
  16. 2017Pointwise Convolutional Neural Networkscited by 127
  17. 2018Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decorationcited by 115
  18. 2021Stylizing 3D Scene via Implicit Representation and HyperNetworkcited by 103
  19. 2017Coherent Online Video Style Transfercited by 96
  20. 2016Fast Patch-based Style Transfer of Arbitrary Stylecited by 92
  21. 2017StyleBank: An Explicit Representation for Neural Image Style Transfercited by 89
  22. 2017Exploring the structure of a real-time, arbitrary neural artistic stylization networkcited by 89
  23. 2020Arbitrary Video Style Transfer via Multi-Channel Correlationcited by 84
  24. 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
  25. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  26. 2020Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Imagecited by 77
  27. 2021Learning to Stylize Novel Viewscited by 76
  28. 2018Arbitrary Style Transfer with Deep Feature Reshufflecited by 75
  29. 2019DeepGCNs: Making GCNs Go as Deep as CNNscited by 72
  30. 20213DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variationscited by 58
  31. 2021SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpaintingcited by 48
  32. 2017Artistic style transfer for videos and spherical imagescited by 45
  33. 2020One Shot 3D Photographycited by 45
  34. 2018Stereoscopic Neural Style Transfercited by 15
  35. 2018Neural Stereoscopic Image Style Transfercited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 14; 2024: 14; 2025: 8; 2026: 2.

45 papers.

Sort:

By area:

  1. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  2. 2022ARF: Artistic Radiance Fieldscited by 147
  3. 2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
  4. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
  5. 2024StyleGaussian: Instant 3D Style Transfer with Gaussian Splattingcited by 79
  6. 2022Unified Implicit Neural Stylizationcited by 67
  7. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  8. 2023AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networkscited by 34
  9. 2023HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3Dcited by 28
  10. 2024Chat-Edit-3D: Interactive 3D Scene Editing via Text Promptscited by 19
  11. 2024Geometry Transfer for Stylizing Radiance Fieldscited by 16
  12. 2024Gaussian Splatting in Stylecited by 16
33 more
  1. 2023Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylizationcited by 14
  2. 2024Reference-based Controllable Scene Stylization with Gaussian Splattingcited by 12
  3. 2023Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Daycited by 11
  4. 2023Creative Birds: Self-Supervised Single-View 3D Style Transfercited by 9
  5. 2023Editing 3D Scenes via Text Prompts without Retrainingcited by 8
  6. 2023ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylizationcited by 6
  7. 2025StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussianscited by 6
  8. 2024ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fieldscited by 5
  9. 2024Freditor: High-Fidelity and Transferable NeRF Editing by Frequency Decompositioncited by 5
  10. 2024G-Style: Stylized Gaussian Splattingcited by 5
  11. 2023VaLID: Variable-Length Input Diffusion for Novel View Synthesiscited by 4
  12. 2024CMC: Few-shot Novel View Synthesis via Cross-view Multiplane Consistencycited by 4
  13. 2025Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Stylescited by 4
  14. 2025Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Stylescited by 4
  15. 2023S2RF: Semantically Stylized Radiance Fieldscited by 3
  16. 2023MuVieCAST: Multi-View Consistent Artistic Style Transfercited by 3
  17. 2024S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenescited by 3
  18. 2024Rethink Arbitrary Style Transfer with Transformer and Contrastive Learningcited by 3
  19. 2025Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splattingcited by 3
  20. 2022LISA: Localized Image Stylization with Audio via Implicit Neural Representationcited by 2
  21. 2024StyleDyRF: Zero-shot 4D Style Transfer for Dynamic Neural Radiance Fieldscited by 2
  22. 2023MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Fieldcited by 1
  23. 2024G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Stylescited by 1
  24. 2026Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Modelscited by 1
  25. 2022Image Style Transfer: from Artistic to Photorealisticcited by 0
  26. 2023Realization RGBD Image Stylizationcited by 0
  27. 2023CLIP3Dstyler: Language Guided 3D Arbitrary Neural Style Transfercited by 0
  28. 2024PNeSM: Arbitrary 3D Scene Stylization via Prompt-Based Neural Style Mappingcited by 0
  29. 2025GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fieldscited by 0
  30. 2025Make Your MoVe: Make Your 3D Contents by Adapting Multi-View Diffusion Models to External Editingcited by 0
  31. 2025SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfercited by 0
  32. 2025Multi-level Dynamic Style Transfer for NeRFscited by 0
  33. 2026Image-Guided Geometric Stylization of 3D Meshescited by 0