Cambricon-SR: An Accelerator for Neural Scene Representation with Sparse Encoding Table
Tianbo Liu, Xinkai Song, Zhifei Yue, Rui Wen, Xing Hu, Zhuoran Song, Yuanbo Wen, Yifan Hao, Wei Li, Zidong Du, Rui Zhang, Jiaming Guo
2025Year
1Citations
1Top-tier citations
Abstract
Neural Scene Representation (NSR) is a promising technique for representing real scenes.By learning from dozens of 2D photos captured from different viewpoints, NSR computes the 3D representation of real scenes.However, the performance of NSR processing running on GPU is insufficient for applications.Cambricon-R achieves high performance of more than 60 scenes per second, but at the cost of modeling quality.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Cited by top-tier papers1
Ask how each one uses itRelated papers
- Cambricon-R: A Fully Fused Accelerator for Real-Time Learning of Neural Scene RepresentationXinkai Song, Yuanbo Wen, Xing Hu, Tianbo Liu et al.MICRO 2023 · 12 citations
- Baking Neural Radiance Fields for Real-Time View SynthesisPeter Hedman, Pratul P. Srinivasan, Ben Mildenhall, Jonathan T. Barron et al.ICCV 2021 · 636 citations
- Equivariant Neural RenderingEmilien Dupont, Miguel Bautista Martin, Alex Colburn, Aditya Sankar et al.ICML 2020 · 69 citations
- 4K4D: Real-Time 4D View Synthesis at 4K ResolutionZhen Xu, Sida Peng, Haotong Lin, Guangzhao He et al.CVPR 2024
- Fast Training of Neural Lumigraph Representations using Meta LearningAlexander W. Bergman, Petr Kellnhofer, Gordon WetzsteinNeurIPS 2021 · 44 citations
