Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
This addresses the challenge of comprehensive 3D scene understanding for applications like robotics and augmented reality, though it is incremental in combining existing tasks with new connections.
The paper tackles the joint problem of 3D holistic scene parsing and human pose estimation from a single-view image, leveraging human-object interaction and physical commonsense to improve performance, with experimental results showing significant improvements on three datasets.
We propose a new 3D holistic++ scene understanding problem, which jointly tackles two tasks from a single-view image: (i) holistic scene parsing and reconstruction---3D estimations of object bounding boxes, camera pose, and room layout, and (ii) 3D human pose estimation. The intuition behind is to leverage the coupled nature of these two tasks to improve the granularity and performance of scene understanding. We propose to exploit two critical and essential connections between these two tasks: (i) human-object interaction (HOI) to model the fine-grained relations between agents and objects in the scene, and (ii) physical commonsense to model the physical plausibility of the reconstructed scene. The optimal configuration of the 3D scene, represented by a parse graph, is inferred using Markov chain Monte Carlo (MCMC), which efficiently traverses through the non-differentiable joint solution space. Experimental results demonstrate that the proposed algorithm significantly improves the performance of the two tasks on three datasets, showing an improved generalization ability.