SyncNoise: Geometrically Consistent Noise Prediction for Instruction-based 3D Editing
Ruihuang Li, Liyi Chen, Zhengqiang Zhang, Varun Jampani, Vishal M. Patel, Lei Zhang
Abstract
Text-based 2D diffusion models have demonstrated impressive capabilities in image generation and editing. Meanwhile, the 2D diffusion models also exhibit substantial potentials for 3D editing tasks. However, how to achieve consistent edits across multiple viewpoints remains a challenge. While the iterative dataset update method is capable of achieving global consistency, it suffers from slow convergence and over-smoothed textures. We propose SyncNoise, a novel geometry-guided multi-view consistent noise editing approach for high-fidelity 3D scene editing. SyncNoise synchronously edits multiple views with 2D diffusion models while enforcing multi-view noise predictions to be geometrically consistent, which ensures global consistency in both semantic structure and low-frequency appearance. To further enhance local consistency in high-frequency details, we set a group of anchor views and propagate them to their neighboring frames through cross-view reprojection. To improve the reliability of multi-view correspondences, we introduce depth supervision during training to enhance the reconstruction of precise geometries. Our method achieves high-quality 3D editing results respecting the textual instructions, especially in scenes with complex textures, by enhancing geometric consistency at the noise and pixel levels.
BibTeX
@article{Li_Chen_Zhang_Jampani_Patel_Zhang_2025, title={SyncNoise: Geometrically Consistent Noise Prediction for Instruction-based 3D Editing}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32519}, DOI={10.1609/aaai.v39i5.32519}, abstractNote={Text-based 2D diffusion models have demonstrated impressive capabilities in image generation and editing. Meanwhile, the 2D diffusion models also exhibit substantial potentials for 3D editing tasks. However, how to achieve consistent edits across multiple viewpoints remains a challenge. While the iterative dataset update method is capable of achieving global consistency, it suffers from slow convergence and over-smoothed textures. We propose SyncNoise, a novel geometry-guided multi-view consistent noise editing approach for high-fidelity 3D scene editing. SyncNoise synchronously edits multiple views with 2D diffusion models while enforcing multi-view noise predictions to be geometrically consistent, which ensures global consistency in both semantic structure and low-frequency appearance. To further enhance local consistency in high-frequency details, we set a group of anchor views and propagate them to their neighboring frames through cross-view reprojection. To improve the reliability of multi-view correspondences, we introduce depth supervision during training to enhance the reconstruction of precise geometries. Our method achieves high-quality 3D editing results respecting the textual instructions, especially in scenes with complex textures, by enhancing geometric consistency at the noise and pixel levels.}, number={5}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Li, Ruihuang and Chen, Liyi and Zhang, Zhengqiang and Jampani, Varun and Patel, Vishal M. and Zhang, Lei}, year={2025}, month={Apr.}, pages={4905-4913} }