MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
This addresses the challenge of efficient and accurate 3D scene generation for applications in computer vision and graphics, representing a novel paradigm rather than an incremental improvement.
The paper tackles the problem of generating compositional 3D scenes from a single image by introducing MIDI, which extends pre-trained image-to-3D models to simultaneously generate multiple 3D instances with accurate spatial relationships, achieving state-of-the-art performance validated on synthetic, real-world, and stylized scene data.
This paper introduces MIDI, a novel paradigm for compositional 3D scene generation from a single image. Unlike existing methods that rely on reconstruction or retrieval techniques or recent approaches that employ multi-stage object-by-object generation, MIDI extends pre-trained image-to-3D object generation models to multi-instance diffusion models, enabling the simultaneous generation of multiple 3D instances with accurate spatial relationships and high generalizability. At its core, MIDI incorporates a novel multi-instance attention mechanism, that effectively captures inter-object interactions and spatial coherence directly within the generation process, without the need for complex multi-step processes. The method utilizes partial object images and global scene context as inputs, directly modeling object completion during 3D generation. During training, we effectively supervise the interactions between 3D instances using a limited amount of scene-level data, while incorporating single-object data for regularization, thereby maintaining the pre-trained generalization ability. MIDI demonstrates state-of-the-art performance in image-to-scene generation, validated through evaluations on synthetic data, real-world scene data, and stylized scene images generated by text-to-image diffusion models.