mlsanityData to 14 Oct 2026

ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fields

arXiv 2402.01950 ↗First posted 2 Feb 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Most of the existing works on arbitrary 3D NeRF style transfer required retraining on each single style condition. This work aims to achieve zero-shot controlled stylization in 3D scenes utilizing text or visual input as conditioning factors. We introduce ConRF, a novel method of zero-shot stylization. Specifically, due to the ambiguity of CLIP features, we employ a conversion process that maps the CLIP feature space to the style space of a pre-trained VGG network and then refine the CLIP multi-modal knowledge into a style transfer neural radiation field. Additionally, we use a 3D volumetric representation to perform local style transfer. By combining these operations, ConRF offers the capability to utilize either text or images as references, resulting in the generation of sequences with novel views enhanced by global or local stylization. Our experiment demonstrates that ConRF outperforms other existing methods for 3D scene and single-text stylization in terms of visual quality.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 46 of its 64 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

46 of 64 references.

References · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  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. 2020Neural Sparse Voxel Fieldscited by 959
  11. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  12. 2023LERF: Language Embedded Radiance Fieldscited by 543
34 more
  1. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  2. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  3. 2015A Neural Algorithm of Artistic Stylecited by 483
  4. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  5. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
  6. 2017Universal Style Transfer via Feature Transformscited by 354
  7. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  8. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 229
  9. 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
  10. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 198
  11. 2021StyTr2: Image Style Transfer with Transformerscited by 187
  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. 2017Deep Photo Style Transfercited by 168
  15. 2022ARF: Artistic Radiance Fieldscited by 147
  16. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  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. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
  21. 2021Learning to Stylize Novel Viewscited by 76
  22. 2020Arbitrary Style Transfer via Multi-Adaptation Networkcited by 70
  23. 2017Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Lossescited by 69
  24. 2022Unified Implicit Neural Stylizationcited by 67
  25. 2023Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversioncited by 48
  26. 2022UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scenecited by 47
  27. 2022CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfercited by 46
  28. 2017Artistic style transfer for videos and spherical imagescited by 45
  29. 20213D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Imagecited by 45
  30. 2021Language-Driven Image Style Transfercited by 37
  31. 2022Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylizationcited by 35
  32. 2024CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Videocited by 18
  33. 2023Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylizationcited by 14
  34. 2023DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volumecited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 1.

5 papers.

  1. 2024Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matchingcited by 9
  2. 2025Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Stylescited by 4
  3. 2025ClimateGS: Real-Time Climate Simulation with 3D Gaussian Style Transfercited by 2
  4. 2024G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Stylescited by 1
  5. 2026M2StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splattingcited by 0