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.
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: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:2603. 03143v2 Announce Type: replace-cross Abstract: Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm.
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:2606.13345v2 Announce Type: replace Abstract: Existing 3D scene editing methods typically rely on per-scene optimization over explicit 3D representations or cascaded edit-and-reconstruct pipeli...
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: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...
The paper introduces Chat-Edit-3D++ (CE3D++), an interactive 3D and 4D scene editing system that uses a Hash-Atlas network to separate 2D editing from 3D reconstruction. CE3D++ employs a large language model to accept arbitrary textual input, interpret user intent, and autonomously invoke appropriate visual models, enabling multi‑round dialogue and diverse editing effects. The approach is extended to monocular 4D scenes by adding motion constraints and a trajectory dataset, allowing a smaller LLM to schedule up to 30 visual tools accurately.
The paper introduces a framework for instruction‑guided 3D editing that does not require paired 3D supervision. It distills visual, semantic, and geometric knowledge from foundation models into a 3D editing model using a differentiable rendering pipeline, guided by a 2D visual prior from an image editing model and a semantic prior from a Vision‑Language Model. A 3D‑aware Distribution Matching regularization is added to prevent geometric collapse and ensure realistic 3D outputs, leading to superior instruction fidelity and cross‑view consistency compared to state‑of‑the‑art baselines.
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.
arXiv:2602. 04349v3 Announce Type: replace-cross Abstract: 3D editing has emerged as a critical research area to provide users with flexible control over 3D assets.
arXiv:2607.18227v2 Announce Type: replace Abstract: In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and imag...