Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories
Susung Hong, Johanna Suvi Karras, Ricardo Martin-Brualla, Ira Kemelmacher-Shlizerman
2025年份
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper46
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 被引用 11,743 次
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li 等NeurIPS 2022 · 被引用 8,965 次
相关 Paper
- Identity-preserving Distillation Sampling by Fixed-Point IteratorSeonhwa Kim, Jiwon Kim, Soobin Park, Donghoon Ahn 等CVPR 2025
- RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion ModelsOzgur Kara, Bariscan Kurtkaya, Hidir Yesiltepe, James M. Rehg 等CVPR 2024
- Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the WildYanhui Guo, Xinxin Zuo, Peng Dai, Juwei Lu 等NeurIPS 2023 · 被引用 13 次
- Stable Score DistillationHaiming Zhu, Yangyang Xu, Chenshu Xu, Tingrui Shen 等ICCV 2025 · 被引用 2 次
- Local 3D Editing via 3D Distillation of CLIP KnowledgeJunha Hyung, Sungwon Hwang, Daejin Kim, Hyunji Lee 等CVPR 2023
