Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization

doi:arXiv:2410.19483

	Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization
	Liu, Weihang1 ; Zheng, Xue Xian 2; Yu, Jingyi1,3 ; Lou, Xin1,3
	2024-10-25
状态	已发表
摘要	The recent popular radiance field models, exemplified by Neural Radiance Fields (NeRF), Instant-NGP and 3D Gaussian Splat?ting, are designed to represent 3D content by that training models for each individual scene. This unique characteristic of scene representation and per-scene training distinguishes radiance field models from other neural models, because complex scenes necessitate models with higher representational capacity and vice versa. In this paper, we propose content?aware radiance fields, aligning the model complexity with the scene intricacies through Adversarial Content-Aware Quantization (A-CAQ). Specifically, we make the bitwidth of parameters differentiable and train?able, tailored to the unique characteristics of specific scenes and requirements. The proposed framework has been assessed on Instant-NGP, a well-known NeRF variant and evaluated using various datasets. Experimental results demonstrate a notable reduction in computational complexity, while preserving the requisite reconstruction and rendering quality, making it beneficial for practical deployment of radiance fields models.
关键词	Radiance fields Content-aware Quantization Model complexity
语种	英语
DOI	arXiv:2410.19483
相关网址	查看原文
出处	Arxiv
收录类别	PPRN.PPRN
WOS记录号	PPRN:118852028
WOS类目	Computer Science, Software Engineering ; Engineering, Electrical& Electronic
资助项目	Central Guided Local Science and Technology Foundation of China[YDZX20223100001001]
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/452399
专题	信息科学与技术学院_博士生信息科学与技术学院_PI研究组_娄鑫组信息科学与技术学院_PI研究组_虞晶怡组
通讯作者	Lou, Xin
作者单位	1.ShanghaiTech Univ, Shanghai, Peoples R China 2.King Abdullah Univ Sci & Technol, Thuwal, Saudi Arabia 3.Human Machine Collaborat, Key Lab Intelligent Percept, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Liu, Weihang,Zheng, Xue Xian,Yu, Jingyi,et al. Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization. 2024.