Paper Overview
Field: Computer Vision 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 the transformation in scene appearance, the authors introduce a depth-aligned planar floor as a global reference frame, shaded with depth-aware cues. Under this structured conditioning, the image generator produces consistent results under large transformations.
Training and Results
- Two-stage training: first on synthetic multi-object scenes, then on a small number of real-world videos from Objectron
- The system generalizes to complex in-the-wild real images
- Works directly on real photographs and significantly outperforms recent state-of-the-art methods on large-scale 3D editing
- Paper: https://arxiv.org/abs/2506.18495