computer-vision

Indoor Scene Synthesis

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in indoor-scene-synthesis

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find indoor-scene-synthesis models and implementations

Datasets

Rent3D++

Subtasks

No subtasks available.

Most implemented papers

LUMINOUS: Indoor Scene Generation for Embodied AI Challenges

Kaixiang Lin, Zhiwei Jia, Qiaozi Gao, Yizhou Zhao, Govind Thattai, J. Thomason, G. Sukhatme•Tue Nov 09 2021

Luminous is the first research framework that employs state-of-the-art indoor scene synthesis algorithms to generate large-scale simulated scenes for Embodied AI challenges, and automatically and quantitatively evaluates the quality of generated indoor scenes via their ability to support complex household tasks.

20

Content

0

Paper Graph

Human-Centric Indoor Scene Synthesis Using Stochastic Grammar

Song-Chun Zhu, Yixin Zhu, Siyuan Huang, Siyuan Qi, Chenfanfu Jiang•Thu May 31 2018

A human-centric method to sample and synthesize 3D room layouts and 2D images thereof, to obtain large-scale 2D/3D image data with the perfect per-pixel ground truth is presented.

194 0

Paper Graph

End-to-End Optimization of Scene Layout

Jiajun Wu, J. Tenenbaum, Zhoutong Zhang, Andrew Luo•Sun May 31 2020

An end-to-end variational generative model for scene layout synthesis conditioned on scene graphs that achieves higher accuracy and diversity in conditional scene synthesis and allows exemplar-based scene generation from various input forms is proposed.

76 0

Paper Graph

Adding a benchmark result helps the community track progress.