Learning View Selection for 3D Scenes
Yifan Sun, Qixing Huang, Dun-Yu Hsiao, Li Guan, Gang Hua
Abstract
We present a method that optimizes max-coverage camera placement based on learning. Given the real scene model with the areas of interest (marked as black blocks) that require to be covered by a set of cameras, we learn a continuous scoring function and apply continuous optimization on camera poses to improve the global coverage score. In this figure, the red area in the top view of a scene indicates that the coverage increases after optimization.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Related papers
- SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric IntegrationAntoine Guédon, Pascal Monasse, Vincent LepetitNeurIPS 2022 · 26 citations
- GANmouflage: 3D Object Nondetection with Texture FieldsRui Guo, Jasmine Collins, Oscar de Lima, Andrew OwensCVPR 2023
- 4D Gaussian Splatting SLAMYanyan Li, Youxu Fang, Zunjie Zhu, Kunyi Li et al.ICCV 2025 · 3 citations
- ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion CaptureSena Kiciroglu, Helge Rhodin, Sudipta N. Sinha, Mathieu Salzmann et al.CVPR 2020
- Chat2Map: Efficient Scene Mapping from Multi-Ego ConversationsSagnik Majumder, Hao Jiang, Pierre Moulon, Ethan Henderson et al.CVPR 2023
