SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

• URL: http://arxiv.org/abs/2604.04911v2
• Date: Wed, 08 Apr 2026 04:54:06 GMT
• Title: SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
• Abstract summary: Image spatial editing performs geometry-driven transformations, allowing precise control over object layout and camera viewpoints.<n>Current models are insufficient for fine-grained spatial manipulations, motivating a dedicated assessment suite.<n>We introduce SpatialEdit-Bench, a complete benchmark that evaluates spatial editing.<n>We construct SpatialEdit-500k, a synthetic dataset generated with a controllable Blender pipeline.
• Score: 85.49998134609665
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image spatial editing performs geometry-driven transformations, allowing precise control over object layout and camera viewpoints. Current models are insufficient for fine-grained spatial manipulations, motivating a dedicated assessment suite. Our contributions are listed: (i) We introduce SpatialEdit-Bench, a complete benchmark that evaluates spatial editing by jointly measuring perceptual plausibility and geometric fidelity via viewpoint reconstruction and framing analysis. (ii) To address the data bottleneck for scalable training, we construct SpatialEdit-500k, a synthetic dataset generated with a controllable Blender pipeline that renders objects across diverse backgrounds and systematic camera trajectories, providing precise ground-truth transformations for both object- and camera-centric operations. (iii) Building on this data, we develop SpatialEdit-16B, a baseline model for fine-grained spatial editing. Our method achieves competitive performance on general editing while substantially outperforming prior methods on spatial manipulation tasks. All resources will be made public at https://github.com/EasonXiao-888/SpatialEdit.

Related papers

• SpatialDiff: 3D-Aware Object Movement via Implicit Spatial Modeling [60.4038189368113]
  We introduce Implicit 3D Spatial Modeling, which introduces 3D prior knowledge and enables the model to internally build a comprehensive understanding of the three-dimensional spatial structure.<n>We also present Global Spatial Supervision, which constrains the latent spatial features to enable the model to perceive changes in object spatial positions caused by editing operations.<n> Experimental results demonstrate that our method significantly improves the accuracy and fidelity of spatial movement in complex scenes.
  arXiv  Detail & Related papers  (2026-08-22T04:46:08Z)
• InterCoG: Towards Spatially Precise Image Editing with Interleaved Chain-of-Grounding Reasoning [60.799998743918955]
  We propose a novel text-vision Interleaved Chain-of-Grounding reasoning framework for fine-grained image editing in complex real-world scenes.<n>The key insight of InterCoG is to first perform object position reasoning solely within text.<n>We also propose two auxiliary training modules: multimodal grounding reconstruction supervision and multimodal grounding reasoning alignment.
  arXiv  Detail & Related papers  (2026-03-02T08:13:16Z)
• Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers [41.08668138583002]
  GeoEdit is a framework that integrates geometric transformations for precise object edits.<n>Effects-context Attention enhances the modeling of intricate lighting and shadow effects for improved realism.<n> RS-Objects is a large-scale geometric editing dataset containing over 120,000 high-quality image pairs.
  arXiv  Detail & Related papers  (2026-02-09T08:39:47Z)
• LocateEdit-Bench: A Benchmark for Instruction-Based Editing Localization [21.62979058692505]
  We propose a large-scale dataset comprising $231$K edited images to benchmark forgery localization methods.<n>Our dataset incorporates four cutting-edge editing models and covers three common edit types.<n>Our work establishes a foundation to keep pace with the evolving landscape of image editing, thereby facilitating the development of effective methods for future forgery localization.
  arXiv  Detail & Related papers  (2026-02-05T12:01:09Z)
• World-Shaper: A Unified Framework for 360° Panoramic Editing [57.174341220144605]
  Existing perspective-based image editing methods fail to model the spatial structure of panoramas.<n>We present World-Shaper, a unified geometry-aware framework that bridges panoramic generation and editing within a single editing-centric design.<n>Our method achieves superior geometric consistency, editing fidelity, and text controllability compared to SOTA methods.
  arXiv  Detail & Related papers  (2026-01-30T19:38:54Z)
• Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation [12.982001613987315]
  G2Editor is a framework designed for imprecise and precise object editing in driving videos.<n>A scene-level 3D bounding box layout is employed to reconstruct occluded areas of non-target objects.<n>Experiments demonstrate that G2Editor effectively supports object repositioning, insertion and deletion within a unified framework.
  arXiv  Detail & Related papers  (2025-08-28T06:39:53Z)
• Training-free Geometric Image Editing on Diffusion Models [53.38549950608886]
  We tackle the task of geometric image editing, where an object within an image is repositioned, reoriented, or reshaped.<n>We propose a decoupled pipeline that separates object transformation, source region inpainting, and target region refinement.<n>Both inpainting and refinement are implemented using a training-free diffusion approach, FreeFine.
  arXiv  Detail & Related papers  (2025-07-31T07:36:00Z)
• SphereDrag: Spherical Geometry-Aware Panoramic Image Editing [53.87789202723925]
  We propose SphereDrag, a novel panoramic editing framework utilizing spherical geometry knowledge for accurate and controllable editing.<n>Specifically, adaptive reprojection (AR) uses adaptive spherical rotation to deal with discontinuity; great-circle trajectory adjustment (GCTA) tracks the movement trajectory more accurate.<n>Also, we construct PanoBench, a panoramic editing benchmark, including complex editing tasks involving multiple objects and diverse styles, which provides a standardized evaluation framework.
  arXiv  Detail & Related papers  (2025-06-13T15:13:09Z)
• PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation [15.342060815068347]
  PixelMan is an inversion-free and training-free method for achieving consistent object editing via Pixel Manipulation and generation.<n>We show that in as few as 16 inference steps, PixelMan outperforms a range of state-of-the-art training-based and training-free methods.
  arXiv  Detail & Related papers  (2024-12-18T19:24:15Z)

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.