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.
Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent across views. We introduce EditBench3D, a repres...
arXiv:2508.01684v2 Announce Type: replace Abstract: While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains...
arXiv:2609.14899v1 Announce Type: new Abstract: Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent...
arXiv:2511.22228v3 Announce Type: replace-cross Abstract: Recent advancements in diffusion and flow models have greatly improved text-based image editing, yet methods that edit images independently o...
arXiv:2609.13318v1 Announce Type: cross Abstract: 3D point-cloud observations are inherently ambiguous in complex, cluttered manipulation scenes, where target objects may be partially occluded or tig...
arXiv:2603. 03143v2 Announce Type: replace-cross Abstract: Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm.
arXiv:2606. 05142v1 Announce Type: cross Abstract: Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customization.
The paper introduces a Dual-Transformer architecture with Cross-Attention for multi-camera view recommendation, achieving a 56.60% Precision@0.5 on the TVMCE dataset, surpassing the previous best of 37.16%. The model separates temporal encoding of past frames from candidate view querying, and an ablation study shows the SwinV2 backbone yields 69.65% Precision@0.5. Fine‑tuning with as little as 20% of a target video improves precision, suggesting efficient personalization for specific editing styles.
Multi-camera systems are foundational to modern media production, and multi-camera editing is a critical task. This involves the proper selection of the appropriate camera view at each moment. In this...
arXiv:2607.07187v2 Announce Type: replace Abstract: Local editing of 3D objects remains a long-standing challenge. When interacting with 3D content, humans naturally tend to specify a coarse region o...
arXiv:2507. 11061v3 Announce Type: replace-cross Abstract: Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content.
arXiv:2601.14056v2 Announce Type: replace-cross Abstract: Training robust visual surveillance models requires large-scale datasets with precise spatial annotations, yet collecting real surveillance d...