Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories
Susung Hong, Johanna Suvi Karras, Ricardo Martin-Brualla, Ira Kemelmacher-Shlizerman
2025Year
Abstract
2 Google Research "… holding a champagne flute" "… a black leather jacket …" "… flats with roses" Figure 1. Perturb-and-Revise takes a source NeRF and an edit prompt as input and produces the edited result through: (1) versatile initialization via parameter perturbation, (2) multi-view consistent score distillation, and (3) refinement with the identity-preserving gradient.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Builds on46
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
Related papers
- Identity-preserving Distillation Sampling by Fixed-Point IteratorSeonhwa Kim, Jiwon Kim, Soobin Park, Donghoon Ahn et al.CVPR 2025
- RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion ModelsOzgur Kara, Bariscan Kurtkaya, Hidir Yesiltepe, James M. Rehg et al.CVPR 2024
- Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the WildYanhui Guo, Xinxin Zuo, Peng Dai, Juwei Lu et al.NeurIPS 2023 · 13 citations
- Stable Score DistillationHaiming Zhu, Yangyang Xu, Chenshu Xu, Tingrui Shen et al.ICCV 2025 · 2 citations
- Local 3D Editing via 3D Distillation of CLIP KnowledgeJunha Hyung, Sungwon Hwang, Daejin Kim, Hyunji Lee et al.CVPR 2023
