cs.CVNov 14, 2026

DecoEdit: Beyond Flat Control for 3D-Aware Unified Image Editing

Authors: Xiaotang Gai, Jinbo Xing, Zijie Meng, Jiayi Yi, Jimin Xiao, Yixuan Qian, Yu Liu, Chaojie Mao, 

Organizations: Zhejiang University · Alibaba Group · University of Illinois at Urbana-Champaign

Abstract

While recent advances in multimodal image editing have achieved impressive results, current frameworks remain largely confined to ``flat" 2D controls (e.g., text prompts, bounding boxes, or masks). Precise 3D-aware geometric manipulation -- such as coordinating an object's location, physical scale, and 3D orientation while strictly preserving its fine-grained identity -- remains an elusive challenge, typically suffering from severe detail degradation or requiring expensive per-instance fine-tuning. In this paper, we present DecoEdit, an all-in-one image editing framework that goes beyond flat control by seamlessly integrating 1D textual, 2D spatial, and 3D volumetric inputs under a unified architecture. First, to power this unified model, we establish a data curation pipeline and curate a large-scale dataset, namely DecoDataset, containing 1.6 million samples, encompassing diverse multi-dimensional (1D/2D/3D) tasks and their complex compositions. Furthermore, we establish a comprehensive image editing benchmark named DecoBench to systematically evaluate multi-task editing performance. Finally, to address the fundamental trade-off between complex spatial transformations and identity preservation, we propose a novel decoupled pipeline: DecoEdit factorizes the editing process by utilizing structural guidance from SAM-3D to anchor the target geometry, scale, and spatial orientation, while concurrently leveraging a detail-preservation path to lock in high-fidelity textures. Extensive experiments demonstrate that DecoEdit achieves state-of-the-art results. Notably, on the challenging 3D spatial pose and orientation control tasks, DecoEdit significantly outperforms leading closed-source models such as Seedream 5.0 in both geometric accuracy and identity consistency.

Figures & tables

Explore similar work

CardsList
  1. BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing

    Jun 22, 2026Feifei Wang, Shiyuan Yang, Xiaoyu Li +1Image EditingVisual Prompt Learning

  2. ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGS Models

    Mar 30, 2026Yuhuan Xie, Aoxuan Pan, Yi-Hua Huang +43D Shape EditingDeformable Object Manipulation

  3. Vinedresser3D: Agentic Text-guided 3D Editing

    Feb 23, 2026Yankuan Chi, Xiang Li, Zixuan Huang +1Text-Guided 3D Scene Editing3D Asset Editing