Edit3r: Instant 3D Scene Editing from Sparse Unposed Images

• URL: http://arxiv.org/abs/2512.25071v1
• Date: Wed, 31 Dec 2025 18:59:53 GMT
• Title: Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
• Authors: Jiageng Liu, Weijie Lyu, Xueting Li, Yejie Guo, Ming-Hsuan Yang,
• Abstract summary: We present Edit3r, a framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images.<n>We show that Edit3r achieves superior semantic alignment and enhanced 3D consistency compared to recent baselines.
• Score: 40.421700685587346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Edit3r, a feed-forward framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images. Unlike prior methods requiring per-scene optimization, Edit3r directly predicts instruction-aligned 3D edits, enabling fast and photorealistic rendering without optimization or pose estimation. A key challenge in training such a model lies in the absence of multi-view consistent edited images for supervision. We address this with (i) a SAM2-based recoloring strategy that generates reliable, cross-view-consistent supervision, and (ii) an asymmetric input strategy that pairs a recolored reference view with raw auxiliary views, encouraging the network to fuse and align disparate observations. At inference, our model effectively handles images edited by 2D methods such as InstructPix2Pix, despite not being exposed to such edits during training. For large-scale quantitative evaluation, we introduce DL3DV-Edit-Bench, a benchmark built on the DL3DV test split, featuring 20 diverse scenes, 4 edit types and 100 edits in total. Comprehensive quantitative and qualitative results show that Edit3r achieves superior semantic alignment and enhanced 3D consistency compared to recent baselines, while operating at significantly higher inference speed, making it promising for real-time 3D editing applications.

Related papers

• Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing [106.07976338405793]
  Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm.<n>We propose textbfRL3DEdit, a single-pass framework driven by reinforcement learning with novel rewards derived from the 3D foundation model, VGGT.<n>Experiments demonstrate that RL3DEdit achieves stable multi-view consistency and outperforms state-of-the-art methods in editing quality with high efficiency.
  arXiv  Detail & Related papers  (2026-03-03T16:31:10Z)
• Fast Multi-view Consistent 3D Editing with Video Priors [19.790628738739354]
  We propose generative Video Prior based 3D Editing (ViP3DE)<n>Our key insight is to condition the video generation model on a single edited view to generate other consistent edited views for 3D updating directly.<n>Our proposed ViP3DE can achieve high-quality 3D editing results even within a single forward pass, significantly outperforming existing methods in both editing quality and speed.
  arXiv  Detail & Related papers  (2025-11-28T13:31:10Z)
• Free-Form Scene Editor: Enabling Multi-Round Object Manipulation like in a 3D Engine [83.0145525456509]
  We present FFSE, a 3D-aware framework designed to enable intuitive, physically-consistent object editing on real-world images.<n>Unlike previous approaches that either operate in image space or require slow and error-prone 3D reconstruction, FFSE models editing as a sequence of learned 3D transformations.<n>To support learning of multi-round 3D-aware object manipulation, we introduce 3DObjectEditor.
  arXiv  Detail & Related papers  (2025-11-17T18:57:39Z)
• C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editing [37.439731931558036]
  C3Editor is a controllable and consistent 2D-lifting-based 3D editing framework.<n>Our method selectively establishes a view-consistent 2D editing model to achieve superior 3D editing results.<n>Our approach delivers more consistent and controllable 2D and 3D editing results than existing 2D-lifting-based methods.
  arXiv  Detail & Related papers  (2025-10-06T07:07:14Z)
• DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing [72.54566271694654]
  We consider the problem of editing 3D objects and scenes based on open-ended language instructions.<n>A common approach to this problem is to use a 2D image generator or editor to guide the 3D editing process.<n>This process is often inefficient due to the need for iterative updates of costly 3D representations.
  arXiv  Detail & Related papers  (2024-04-29T17:59:30Z)
• View-Consistent 3D Editing with Gaussian Splatting [50.6460814430094]
  View-consistent Editing (VcEdit) is a novel framework that seamlessly incorporates 3DGS into image editing processes.<n>By incorporating consistency modules into an iterative pattern, VcEdit proficiently resolves the issue of multi-view inconsistency.
  arXiv  Detail & Related papers  (2024-03-18T15:22:09Z)
• Real-time 3D-aware Portrait Editing from a Single Image [111.27169315556444]
  3DPE can edit a face image following given prompts, like reference images or text descriptions. A lightweight module is distilled from a 3D portrait generator and a text-to-image model.
  arXiv  Detail & Related papers  (2024-02-21T18:36:26Z)
• Free-Editor: Zero-shot Text-driven 3D Scene Editing [8.966537479017951]
  Training a diffusion model specifically for 3D scene editing is challenging due to the scarcity of large-scale datasets. We introduce a novel, training-free 3D scene editing technique called textscFree-Editor, which enables users to edit 3D scenes without the need for model retraining. Our method effectively addresses the issue of multi-view style inconsistency found in state-of-the-art (SOTA) methods.
  arXiv  Detail & Related papers  (2023-12-21T08:40:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.