Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces LB-Edit, a novel framework for text-driven 3D scene editing that optimizes camera placement and multi-view alignment to enhance the editing process. By utilizing Attention-Guided Editing Camera Placement (ACP) and Multi-view Attention Alignment (MAA), the framework ensures localized edits are consistent across multiple views while significantly improving user preference metrics such as instruction fidelity and editing locality. Experiments demonstrate that LB-Edit achieves superior results with fewer editing views and reduced latency compared to existing methods.
Achieving up to 7x faster editing with fewer views, LB-Edit redefines how we approach 3D scene editing by ensuring consistency and fidelity across multiple perspectives.
Text-driven 3D scene editing with 3D Gaussian Splatting (3DGS) typically applies a 2D diffusion editor to views rendered from fixed training cameras, limiting both the spatial coverage of edits and the user's freedom to target specific objects in complex scenes. We present LB-Edit, a framework that addresses two coupled problems: where to place editing cameras for localized edits, and how to make per-view edits agree with one another so that the 3D scene remains consistent after fine-tuning. First, Attention-Guided Editing Camera Placement (ACP) probes the diffusion model's self- and cross-attention at multiple candidate camera distances to find where attention is well-contained in the region of interest, then places a compact, geometrically diverse editing camera set at that attention-optimal distance. Second, Multi-view Attention Alignment (MAA) steers the editor toward the same edit across views along two axes: it aligns appearance by sharing self-attention features via token-level correspondence, and aligns spatial location by lifting cross-attention maps onto the 3D Gaussians as a shared 3D attention field, suppressing both appearance and spatial drift. Experiments on multi-object and single-object scenes show that our method achieves the highest user preference in instruction fidelity, multi-view consistency, and editing locality, using as few as 5 editing views and reducing latency by up to 7x over existing methods.