Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense

Abstract

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.

arXiv commentAccepted by ICCV 2019

References in corpus (3)

• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
• Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars

Cited by in corpus (7)

• Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
• Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity
• Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
• Generating 3D People in Scenes without People
• Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing
• Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
• DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization