mlsanityData to 14 Oct 2026

Geometry Transfer for Stylizing Radiance Fields

arXiv 2402.00863 ↗First posted 1 Feb 2024cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Shape and geometric patterns are essential in defining stylistic identity. However, current 3D style transfer methods predominantly focus on transferring colors and textures, often overlooking geometric aspects. In this paper, we introduce Geometry Transfer, a novel method that leverages geometric deformation for 3D style transfer. This technique employs depth maps to extract a style guide, subsequently applied to stylize the geometry of radiance fields. Moreover, we propose new techniques that utilize geometric cues from the 3D scene, thereby enhancing aesthetic expressiveness and more accurately reflecting intended styles. Our extensive experiments show that Geometry Transfer enables a broader and more expressive range of stylizations, thereby significantly expanding the scope of 3D style transfer.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 74 of its 90 references that are in the map. First posted on arXiv 1 Feb 2024.

Builds on

74 of 90 references.

References · 74

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  6. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  9. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  10. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  11. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  12. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
38 more
  1. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 471
  2. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  3. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
  4. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  5. 2017Universal Style Transfer via Feature Transformscited by 354
  6. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  7. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 198
  8. 2021AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfercited by 178
  9. 2022Panoptic Lifting for 3D Scene Understanding with Neural Fieldscited by 174
  10. 2017Deep Photo Style Transfercited by 168
  11. 2019Style Transfer by Relaxed Optimal Transport and Self-Similaritycited by 168
  12. 2022ARF: Artistic Radiance Fieldscited by 147
  13. 2018The Contextual Loss for Image Transformation with Non-Aligned Datacited by 135
  14. 2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
  15. 2017Visual Attribute Transfer through Deep Image Analogycited by 123
  16. 2017Deep Image Harmonizationcited by 120
  17. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  18. 2020Cross-domain Correspondence Learning for Exemplar-based Image Translationcited by 116
  19. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  20. 2018Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decorationcited by 115
  21. 2021Stylizing 3D Scene via Implicit Representation and HyperNetworkcited by 103
  22. 2016Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesiscited by 102
  23. 2017Coherent Online Video Style Transfercited by 96
  24. 2016Fast Patch-based Style Transfer of Arbitrary Stylecited by 92
  25. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
  26. 2021Learning to Stylize Novel Viewscited by 76
  27. 2018Arbitrary Style Transfer with Deep Feature Reshufflecited by 75
  28. 2020Arbitrary Style Transfer via Multi-Adaptation Networkcited by 70
  29. 2017Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Lossescited by 69
  30. 2022Unified Implicit Neural Stylizationcited by 67
  31. 2019Deep Image Blendingcited by 62
  32. 2022Harmonizer: Learning to Perform White-Box Image and Video Harmonizationcited by 61
  33. 20193DN: 3D Deformation Networkcited by 60
  34. 2018A Style-Aware Content Loss for Real-time HD Style Transfercited by 58
  35. 2021StyleMesh: Style Transfer for Indoor 3D Scene Reconstructionscited by 58
  36. 2018Learning Linear Transformations for Fast Arbitrary Style Transfercited by 48
  37. 2023Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversioncited by 48
  38. 2022CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfercited by 46

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 9; 2025: 4; 2026: 3.

16 papers.

Sort:

By area:

  1. 2024Garment3DGen: 3D Garment Stylization and Texture Generationcited by 26
  2. 2024SGSST: Scaling Gaussian Splatting StyleTransfercited by 20
  3. 20243D Mesh Editing using Masked LRMscited by 18
  4. 2024Gaussian Splatting in Stylecited by 16
  5. 2025Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Stylescited by 4
  6. 2024WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussianscited by 3
  7. 20244DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splattingcited by 3
  8. 2025GT2-GS: Geometry-aware Texture Transfer for Gaussian Splattingcited by 3
  9. 2025FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splattingcited by 3
  10. 2024CRAFT: Designing Creative and Functional 3D Objectscited by 2
  11. 2026Thinking Like Van Gogh: Structure-Aware Style Transfer via Flow-Guided 3D Gaussian Splattingcited by 1
  12. 2024Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Modelscited by 0
4 more
  1. 2024ExCellGen: Fast, Controllable, Photorealistic 3D Scene Generation from a Single Real-World Exemplarcited by 0
  2. 2025GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fieldscited by 0
  3. 2026Image-Guided Geometric Stylization of 3D Meshescited by 0
  4. 2026Geometry-Aware Style Transfer in 3D Gaussian Splattingcited by 0