3DP3: 3D Scene Perception via Probabilistic Programming
This work addresses scene perception for robotics or computer vision by providing a structured approach that improves accuracy and generalization, though it appears incremental as it builds on existing generative models and inference techniques.
The authors tackled the problem of 3D scene understanding from RGB-D images by developing 3DP3, a framework that uses probabilistic programming for inverse graphics, and demonstrated it achieves higher accuracy in 6DoF object pose estimation and better generalization to novel scenes compared to deep learning baselines.
We present 3DP3, a framework for inverse graphics that uses inference in a structured generative model of objects, scenes, and images. 3DP3 uses (i) voxel models to represent the 3D shape of objects, (ii) hierarchical scene graphs to decompose scenes into objects and the contacts between them, and (iii) depth image likelihoods based on real-time graphics. Given an observed RGB-D image, 3DP3's inference algorithm infers the underlying latent 3D scene, including the object poses and a parsimonious joint parametrization of these poses, using fast bottom-up pose proposals, novel involutive MCMC updates of the scene graph structure, and, optionally, neural object detectors and pose estimators. We show that 3DP3 enables scene understanding that is aware of 3D shape, occlusion, and contact structure. Our results demonstrate that 3DP3 is more accurate at 6DoF object pose estimation from real images than deep learning baselines and shows better generalization to challenging scenes with novel viewpoints, contact, and partial observability.