mlsanityData to 14 Oct 2026

NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs

arXiv 2402.08622 ↗First posted 13 Feb 2024cs.CV cs.GRcited by 11

Not on the map. Why?

Abstract (arXiv)

A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and appearance of a scene. We here ask the question whether we can transfer the appearance from a source NeRF onto a target 3D geometry in a semantically meaningful way, such that the resulting new NeRF retains the target geometry but has an appearance that is an analogy to the source NeRF. To this end, we generalize classic image analogies from 2D images to NeRFs. We leverage correspondence transfer along semantic affinity that is driven by semantic features from large, pre-trained 2D image models to achieve multi-view consistent appearance transfer. Our method allows exploring the mix-and-match product space of 3D geometry and appearance. We show that our method outperforms traditional stylization-based methods and that a large majority of users prefer our method over several typical baselines.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 47 of its 75 references that are in the map. First posted on arXiv 13 Feb 2024.

Builds on

47 of 75 references.

References · 47

  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  6. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  7. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  8. 2015A Neural Algorithm of Artistic Stylecited by 483
  9. 2023Emergent Correspondence from Image Diffusioncited by 446
  10. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 371
  11. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
  12. 2021Advances in Neural Renderingcited by 365
35 more
  1. 2017Universal Style Transfer via Feature Transformscited by 354
  2. 2021Deep ViT Features as Dense Visual Descriptorscited by 330
  3. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
  4. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 301
  5. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 232
  6. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 217
  7. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 214
  8. 2022Splicing ViT Features for Semantic Appearance Transfercited by 209
  9. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 158
  10. 2022ARF: Artistic Radiance Fieldscited by 147
  11. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  12. 2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
  13. 2017Visual Attribute Transfer through Deep Image Analogycited by 123
  14. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  15. 2022DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenescited by 103
  16. 2023SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Fieldcited by 94
  17. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
  18. 2022Deforming Radiance Fields with Cagescited by 78
  19. 2021Learning to Stylize Novel Viewscited by 76
  20. 2019Smooth Shells: Multi-Scale Shape Registration with Functional Mapscited by 72
  21. 2023Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Featurescited by 55
  22. 2022PaletteNeRF: Palette-based Appearance Editing of Neural Radiance Fieldscited by 45
  23. 2023StyleGAN knows Normal, Depth, Albedo, and Morecited by 44
  24. 2023NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Cloudscited by 41
  25. 2021Neural Surface Mapscited by 34
  26. 2023Zero-Shot 3D Shape Correspondencecited by 33
  27. 2023Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fieldscited by 28
  28. 2023Materialistic: Selecting Similar Materials in Imagescited by 26
  29. 2023Locally Stylized Neural Radiance Fieldscited by 20
  30. 2023ProteusNeRF: Fast Lightweight NeRF Editing using 3D-Aware Image Contextcited by 17
  31. 2023Neural Semantic Surface Mapscited by 13
  32. 2022Plateau-reduced Differentiable Path Tracingcited by 10
  33. 2022Learning to Learn and Sample BRDFscited by 9
  34. 2023Dyn-E: Local Appearance Editing of Dynamic Neural Radiance Fieldscited by 5
  35. 2023SO-NeRF: Active View Planning for NeRF using Surrogate Objectivescited by 5

Built on by

Cited by year (2026 to 14 Oct)

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

11 papers.

  1. 2024Beyond Complete Shapes: A Benchmark for Quantitative Evaluation of 3D Shape Surface Matching Algorithmscited by 11
  2. 2024SAMa: Material-aware 3D Selection and Segmentationcited by 10
  3. 20253D Stylization via Large Reconstruction Modelcited by 8
  4. 2025Surface-Aware Distilled 3D Semantic Featurescited by 5
  5. 2026Spanning the Visual Analogy Space with a Weight Basis of LoRAscited by 5
  6. 2025Learning 3D Scene Analogies with Neural Contextual Scene Mapscited by 4
  7. 2026Symmetry Informative and Agnostic Feature Disentanglement for 3D Shapescited by 2
  8. 2024Material Transforms from Disentangled NeRF Representationscited by 1
  9. 2026Beyond Input-Output: Rethinking Creativity through Design-by-Analogy in Human-AI Collaborationcited by 1
  10. 2025PQDAST: Depth-Aware Arbitrary Style Transfer for Games via Perceptual Quality-Guided Distillationcited by 0
  11. 2026Feature-Guided Diffusion for Non-Differentiable Inverse Renderingcited by 0