paper-with-me

홈 › Papers

Human-centric Indoor Scene Synthesis Using Stochastic Grammar

2018-08-25 · CVPR 2018 6 · Siyuan Qi, Yixin Zhu, Siyuan Huang, Chenfanfu Jiang, Song-Chun Zhu

We present a human-centric method to sample and synthesize 3D room layouts and 2D images thereof, to obtain large-scale 2D/3D image data with perfect per-pixel ground truth. An attributed spatial And-Or graph (S-AOG) is proposed to represent indoor scenes. The S-AOG is a probabilistic grammar model, in which the terminal nodes are object entities. Human contexts as contextual relations are encoded by Markov Random Fields (MRF) on the terminal nodes. We learn the distributions from an indoor scene dataset and sample new layouts using Monte Carlo Markov Chain. Experiments demonstrate that our method can robustly sample a large variety of realistic room layouts based on three criteria: (i) visual realism comparing to a state-of-the-art room arrangement method, (ii) accuracy of the affordance maps with respect to groundtruth, and (ii) the functionality and naturalness of synthesized rooms evaluated by human subjects. The code is available at https://github.com/SiyuanQi/human-centric-scene-synthesis.

📄 PDF Abstract BibTeX arXiv:1808.08473

Code (1)

SiyuanQi/human-centric-scene-synthesis 공식 구현

Tasks

Indoor Scene Synthesis

Similar Papers 제목 키워드 기반

Function2Scene: 3D Indoor Scene Layout from Functional Specifications

2026-05-29 · Ruiqi Wang, Qimin Chen, Daniel Ritchie, Angel X. Chang 외 arxiv

Most text-driven 3D indoor scene synthesis methods generate rooms from object-centric prompts, asking what furniture should be placed rather than how the space is used. Yet in real interior design, a layout is judged by …

Indoor Scene Synthesis

Functional 3D Scene Synthesis through Human-Scene Optimization

2025-02-05 · Yao Wei, Matteo Toso, Pietro Morerio, Michael Ying Yang 외

This paper presents a novel generative approach that outputs 3D indoor environments solely from a textual description of the scene. Current methods often treat scene synthesis as a mere layout prediction task, leading to…

Human-Object Interaction DetectionScene Generation

Stochastic Scene-Aware Motion Prediction

2021-08-18 · ICCV 2021 10 · Mohamed Hassan, Duygu Ceylan, Ruben Villegas, Jun Saito 외

A long-standing goal in computer vision is to capture, model, and realistically synthesize human behavior. Specifically, by learning from data, our goal is to enable virtual humans to navigate within cluttered indoor sce…

motion predictionMotion SynthesisNavigatePrediction

LUMINOUS: Indoor Scene Generation for Embodied AI Challenges

2021-11-10 · Yizhou Zhao, Kaixiang Lin, Zhiwei Jia, Qiaozi Gao 외

Learning-based methods for training embodied agents typically require a large number of high-quality scenes that contain realistic layouts and support meaningful interactions. However, current simulators for Embodied AI …

Indoor Scene SynthesisScene Generation

Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis

2025-03-01 · Xuehao Gao, Yang Yang, Shaoyi Du, Guo-Jun Qi 외

As two intimate reciprocal tasks, scene-aware human motion synthesis and analysis require a joint understanding between multiple modalities, including 3D body motions, 3D scenes, and textual descriptions. In this paper, …

DiversityMotion GenerationMotion Synthesis