Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image

ECCV 2018 Siyuan HuangSiyuan QiYixin ZhuYinxue XiaoYuanlu XuSong-Chun Zhu

We propose a computational framework to jointly parse a single RGB image and reconstruct a holistic 3D configuration composed by a set of CAD models using a stochastic grammar model. Specifically, we introduce a Holistic Scene Grammar (HSG) to represent the 3D scene structure, which characterizes a joint distribution over the functional and geometric space of indoor scenes... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.