3D Scene Understanding Through Local Random Access Sequence Modeling
This work addresses a pivotal problem in computer vision for applications in graphics, augmented reality, and robotics, offering a unified framework with incremental improvements over existing methods.
The paper tackled the problem of 3D scene understanding from single images by proposing an autoregressive generative approach called Local Random Access Sequence (LRAS) modeling, which achieved state-of-the-art results in novel view synthesis and 3D object manipulation.
3D scene understanding from single images is a pivotal problem in computer vision with numerous downstream applications in graphics, augmented reality, and robotics. While diffusion-based modeling approaches have shown promise, they often struggle to maintain object and scene consistency, especially in complex real-world scenarios. To address these limitations, we propose an autoregressive generative approach called Local Random Access Sequence (LRAS) modeling, which uses local patch quantization and randomly ordered sequence generation. By utilizing optical flow as an intermediate representation for 3D scene editing, our experiments demonstrate that LRAS achieves state-of-the-art novel view synthesis and 3D object manipulation capabilities. Furthermore, we show that our framework naturally extends to self-supervised depth estimation through a simple modification of the sequence design. By achieving strong performance on multiple 3D scene understanding tasks, LRAS provides a unified and effective framework for building the next generation of 3D vision models.