Research map / 3D vision / NeRF and radiance fields
Local 3D Editing via 3D Distillation of CLIP Knowledge
Junha Hyung, Sungwon Hwang, Daejin Kim, Hyunji Lee, Jaegul Choo
Read the paperCheck 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 LENeRF instead of IDE-3D + StyleCLIP | 3D local editing on FFHQ · FFHQ | PSNR: 12.44 -> 20.86 | Improved |
| use LENeRF instead of IDE-3D + StyleCLIP | 3D local editing on FFHQ · FFHQ | R-precision: 0.61 -> 0.78 | Improved |
| use LENeRF instead of IDE-3D + StyleCLIP | 3D local editing on FFHQ · FFHQ | FID: 4.56 -> 4.37 | Improved |
| use LENeRF instead of IDE-3D + StyleCLIP | 3D local editing on FFHQ · FFHQ | ΔFID: +3.29 -> +2.21 | Improved |
| use LENeRF instead of CLIP-NeRF | 3D local editing on Cats · Cats | FID: 18.6 -> 2.71 | Improved |
| use LENeRF instead of CLIP-NeRF | 3D local editing on Cats · Cats | ΔFID: +12.7 -> +1.94 | Improved |
| add the Attention Field Network for localized feature fusion (ablation) | LENeRF · FFHQ | PSNR: 10.81 -> 20.86 | Improved |
| add the Attention Field Network for localized feature fusion (ablation) | LENeRF · FFHQ | R-precision: 0.66 -> 0.78 | Improved |
| add the Attention Field Network (ablation) | LENeRF · FFHQ | ΔFID: +4.90 -> +2.21 | Improved |
| add the Attention Field Network (ablation) | LENeRF · Cats | ΔFID: +4.17 -> +1.94 | Improved |
| add the Attention Field Network (ablation) | LENeRF · FFHQ | FID: 4.37 -> 4.37 | No clear effect |
| add the Attention Field Network (ablation) | LENeRF · Cats | FID: 2.71 -> 2.71 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CLIP-NeRF — CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields (CVPR 2022) · better on 6 of 6 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
- CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields (CVPR 2022 · similarity 0.90)
- InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image (ICLR 2024 · similarity 0.87)
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.87)
- Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training (CVPR 2024 · similarity 0.87)
- Reference-Based 3D-Aware Image Editing with Triplanes (CVPR 2025 · similarity 0.87)
- ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF (ICLR 2024 · similarity 0.87)
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.
