SeamlessNeRF: Stitching Part NeRFs with Gradient Propagation
DescriptionNeural Radiance Fields (NeRFs) have emerged as a promising representation for 3D scenes, sparking a surge in research aimed at extending the editing capabilities in this domain. The task of seamless editing and merging of different NeRFs, similar to the "copy-and-paste" function in 2D image editing, remains a critical operation that current methods struggle to accomplish. To address these challenges, we propose SeamlessNeRF, a novel approach for seamless merging and editing of multiple NeRFs. Our method optimizes radiance fields within a merged NeRF representation and focuses on the boundary area where different radiance fields intersect, aligning radiance color and preserving the gradient field of the target. This technique allows for a seamless and natural fusion of NeRFs, while overcoming limitations faced by traditional image-based melding methods. To the best of our knowledge, SeamlessNeRF is the first to offer such capabilities, advancing the field of 3D editing with an innovative gradient propagation method for radiance fields. Our method provides a robust solution for complex scene composition and intricate character modeling, validated by extensive experimental results. Through SeamlessNeRF, we make the first step towards a seamless, efficient, and intuitive approach to editing in the realm of 3D representations.
Event Type
Technical Papers
TimeWednesday, 13 December 20233:35pm - 3:45pm
LocationMeeting Room C4.8, Level 4 (Convention Centre)
