文献类型：期刊文献

英文题名：LODNeuS: A Flexible Lightweight Neural Implicit Surface Representation With Unconstrained Viewpoint Rendering

作者：Chen, Zhihua[1];Li, Yuhang[1];Dai, Lei[1];Li, Ping[2];Zhu, Lei[3,4];Sheng, Bin[5,6,7]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Hong Kong Polytech Univ, Sch Design, Dept Comp, Hong Kong, Peoples R China;[3]Hong Kong Univ Sci & Technol Guangzhou, ROAS Thrust, Guangzhou 511453, Peoples R China;[4]Hong Kong Univ Sci & Technol, Dept Elect & Comp Engn, Hong Kong, Peoples R China;[5]Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai 200240, Peoples R China;[6]Shanghai Jiao Tong Univ, Sch Comp Sci, Shanghai 200240, Peoples R China;[7]Shanghai Jiao Tong Univ, AI Inst, MoE Key Lab Artificial Intelligence, Shanghai 200240, Peoples R China

年份：2026

卷号：36

期号：6

起止页码：7540

外文期刊名：IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY

收录：;EI(收录号：20260920150450);WOS:【SCI-EXPANDED(收录号:WOS:001786231600006)】；

基金：This work was supported by the National NaturalScience Foundation of China under Grant T2525004, Grant 62572188, Grant62306113, and Grant 62272164.

语种：英文

外文关键词：Rendering (computer graphics); Three-dimensional displays; Geometry; Image color analysis; Neural radiance field; Visualization; Training; Decoding; Color; Cameras; Neural rendering; implicit geometry representation; level of details

摘要：NeRF-like methods learn implicit 3D neural representations from 2D multiview images, enabling the synthesis of compelling novel views. However, to capture high-fidelity geometry, prior methods often rely on large-scale networks. This dependency hampers the potential applications of neural implicit representations, such as MR visualization. To address this, we introduce LODNeuS, an implicit surface representation based on feature voxel grids. LODNeuS captures multiple LODs of implicit geometry by maintaining voxel grids paired with a set of corresponding lightweight decoders. This allows for high-quality rendering with the ability to dynamically switch between detail levels. Another challenge is that existing methods, both volumetric and surface-based, tend to train and render their representations within a confined space, without explicitly restricting the sampling points properly. This lack of constraints can result in ambiguity, artifacts, and inefficient use of computational resources. We study this effect during free viewpoint rendering using conventional methods and develop an adaptive sampling scheme that emphasizes a valid geometric space for sampling point allocation. Our experimental results show that LODNeuS can match the visual quality of existing methods while offering flexible and lightweight inference. The benefits of adaptive sampling are also demonstrated in the free viewpoint rendering subsection. Our work extends the capabilities of neural implicit representations beyond previously defined limitations, broadening the scope of potential applications.