Holistic 3D Scene Understanding from a Single Image with Implicit Representation
This addresses the challenge of accurate 3D scene reconstruction from cluttered, occluded single images, which is important for applications like robotics and AR/VR, but appears incremental as it builds on existing implicit representation methods.
The paper tackles the ill-posed problem of holistic 3D scene understanding from a single image, which involves predicting object shapes, poses, and layout, and demonstrates that their method outperforms state-of-the-art methods in these tasks.
We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate estimation of both shapes and layout especially for the cluttered scene due to the heavy occlusion between objects. We propose to utilize the latest deep implicit representation to solve this challenge. We not only propose an image-based local structured implicit network to improve the object shape estimation, but also refine the 3D object pose and scene layout via a novel implicit scene graph neural network that exploits the implicit local object features. A novel physical violation loss is also proposed to avoid incorrect context between objects. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods in terms of object shape, scene layout estimation, and 3D object detection.