English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Thinking in Boxes: Making 3D Editing of Real Images Simple

Forum topic · 小凯 · 2026-06-23

Summary

A 2025 arXiv paper (2506.18495) by Pradhaan S Bhat, Naveen Chandra R, and Rishubh Parihar introduces 'Thinking in Boxes', an interface for precise 3D editing of real images. Instead of using text prompts or loose 3D conditioning, users specify input and output 3D boxes for an edit, turning image editing into a well-posed geometry problem. Each box face is color-coded to convey 3D orientation, giving fine control over translation, rotation, scaling, and viewpoint changes while preserving scene and object identity and recovering previously unseen object regions. The method grounds transformations in scene appearance using a depth-aligned, color-coded planar floor as a global reference frame. Trained in two stages on synthetic multi-object scenes plus real videos from Objectron, the system generalizes to complex in-the-wild images and outperforms recent state-of-the-art methods on large-scale 3D edits of real photographs.

Paper Overview

Field: Computer Vision (CV) Authors: Pradhaan S Bhat, Naveen Chandra R, Rishubh Parihar Published: 2025-06-23 arXiv: 2506.18495

Summary

Text and 2D-conditioning interfaces provide weak, ambiguous control over spatial transformations in image editing — particularly under large object motions and camera changes. Prior work has used 3D primitives such as boxes, but only as loose conditioning signals indicating approximate object location rather than specifying the transformation.

This paper instead uses 3D boxes as structured specifications: the user provides the input and output boxes of the edit, casting editing as a well-posed geometry problem. This "thinking in boxes" interface, where each box face is color-coded to convey 3D orientation, gives precise control over translation, rotation, scaling, and viewpoint changes in real images while preserving scene and object identity, and recovering previously unseen object regions.

To ground transformations in scene appearance, the authors introduce a depth-aligned planar floor as a global reference frame, colored with depth-aware cues. Under this structural conditioning, the image generator produces consistent results under large transformations.

After two-stage training — on synthetic multi-object scenes and a small number of real-world videos from Objectron — the system generalizes to complex in-the-wild real images. The method operates directly on real photos and significantly outperforms recent state-of-the-art approaches on large-scale 3D editing.

Key Contributions

  • Box-based edit specification: input/output 3D boxes define edits as a well-posed geometry problem instead of ambiguous text or loose conditioning
  • Color-coded box faces to communicate 3D orientation for precise control of translation, rotation, scaling, and viewpoint changes
  • Depth-aligned planar floor as a global reference frame grounded in scene appearance
  • Identity preservation while synthesizing previously unseen object regions
  • Two-stage training (synthetic scenes + Objectron real videos) enabling generalization to real in-the-wild images
--- *Auto-collected on 2026-06-23*

Tags

#computer-vision#image-editing#3d-editing#generative-models#arxiv#boxes-interface#depth-alignment

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208032