TY - GEN
T1 - Infinigen Indoors
T2 - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
AU - Raistrick, Alexander
AU - Mei, Lingjie
AU - Kayan, Karhan
AU - Yan, David
AU - Zuo, Yiming
AU - Han, Beining
AU - Wen, Hongyu
AU - Parakh, Meenal
AU - Alexandropoulos, Stamatis
AU - Lipson, Lahav
AU - Ma, Zeyu
AU - Deng, Jia
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - We introduce Infinigen Indoors, a Blender-based procedural generator of photorealistic indoor scenes. It builds upon the existing Infinigen system, which focuses on natural scenes, but expands its coverage to indoor scenes by introducing a diverse library of procedural indoor assets, including furniture, architecture elements, appliances, and other day-to-day objects. It also introduces a constraint-based arrangement system, which consists of a domain-specific language for expressing diverse constraints on scene composition, and a solver that generates scene compositions that maximally satisfy the constraints. We provide an export tool that allows the generated 3D objects and scenes to be directly used for training embodied agents in real-time simulators such as Omniverse and Unreal. Infinigen Indoors is open-sourced under the BSD license. Please visit infinigen.org for code and videos.
AB - We introduce Infinigen Indoors, a Blender-based procedural generator of photorealistic indoor scenes. It builds upon the existing Infinigen system, which focuses on natural scenes, but expands its coverage to indoor scenes by introducing a diverse library of procedural indoor assets, including furniture, architecture elements, appliances, and other day-to-day objects. It also introduces a constraint-based arrangement system, which consists of a domain-specific language for expressing diverse constraints on scene composition, and a solver that generates scene compositions that maximally satisfy the constraints. We provide an export tool that allows the generated 3D objects and scenes to be directly used for training embodied agents in real-time simulators such as Omniverse and Unreal. Infinigen Indoors is open-sourced under the BSD license. Please visit infinigen.org for code and videos.
KW - Dataset
KW - Embodied-AI
KW - Indoor
KW - Procedural Generation
KW - Robotics
KW - Synthetic
UR - https://www.scopus.com/pages/publications/85197714361
UR - https://www.scopus.com/inward/citedby.url?scp=85197714361&partnerID=8YFLogxK
U2 - 10.1109/CVPR52733.2024.02058
DO - 10.1109/CVPR52733.2024.02058
M3 - Conference contribution
AN - SCOPUS:85197714361
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 21783
EP - 21794
BT - Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024
PB - IEEE Computer Society
Y2 - 16 June 2024 through 22 June 2024
ER -