Research map / 3D vision / NeRF and radiance fields
CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields
Can Wang, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use feedforward code mappers instead of EditNeRF's per-edit optimization | CLIP-NeRF · Photoshapes chairs and Carla cars, shape and appearance editing | editing time (s): 30.0 -> 0.58; 15.9 -> 0.51; 33.2 -> 2.12; 16.8 -> 1.98 | Improved |
| add the shape deformation network to disentangle shape control (ablation) | CLIP-NeRF · Chairs, shape editing | FID after editing: 53.2 -> 48.4 | Improved |
| add the shape deformation network to disentangle shape control (ablation) | CLIP-NeRF · Cars, shape editing | FID after editing: 71.1 -> 67.8 | Improved |
| add the shape deformation network to disentangle shape control (ablation) | CLIP-NeRF · Chairs, color editing | FID after editing: 54.3 -> 49.0 | Improved |
| add the shape deformation network to disentangle shape control (ablation) | CLIP-NeRF · Cars, color editing | FID after editing: 69.9 -> 67.2 | Improved |
| add a CLIP constraint to the single-view inverse optimization (ablation) | CLIP-NeRF inversion · Real-image inversion | inversion quality | Improved |
Later papers that compared with this method
4 later accepted papers report CLIP-NeRF as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- Colorizing Monochromatic Radiance Fields (AAAI 2024 · better on 5 of 5 shared results)
- Free-Editor: Zero-shot Text-driven 3D Scene Editing (ECCV 2024 · better on 2 of 2 shared results)
- Local 3D Editing via 3D Distillation of CLIP Knowledge (CVPR 2023 · better on 6 of 6 shared results)
- TAPS3D: Text-Guided 3D Textured Shape Generation From Pseudo Supervision (CVPR 2023 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields (ICCV 2023 · similarity 0.91)
- Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields (ICCV 2023 · similarity 0.91)
- Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates (CVPR 2024 · similarity 0.90)
- HyperFields: Towards Zero-Shot Generation of NeRFs from Text (ICML 2024 · similarity 0.88)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.88)
- NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
