Skip to main content

ORIGINAL RESEARCH article

Front. Neurorobot.

Volume 19 - 2025 | doi: 10.3389/fnbot.2025.1558948

HR-NeRF: Advancing Realism and Accuracy in Highlight Scene Representation

Provisionally accepted
  • Chuzhou Polytechnic, Chuzhou, China

The final, formatted version of the article will be published soon.

    NeRF and its variants excel in novel view synthesis but struggle with scenes featuring specular highlights. To address this limitation, we introduce the Highlight Recovery Network (HRNet), a new architecture that enhances NeRF's ability to capture specular scenes. HRNet incorporates Swish activation functions, affine transformations, multilayer perceptrons (MLPs), and residual blocks, which collectively enable smooth non-linear transformations, adaptive feature scaling, and hierarchical feature extraction. The residual connections help mitigate the vanishing gradient problem, ensuring stable training. Despite the simplicity of HRNet's components, it achieves impressive results in recovering specular highlights. Additionally, a density voxel grid enhances model efficiency. Evaluations on four inward-facing benchmarks demonstrate that our approach outperforms NeRF and its variants, achieving a 3∼5 dB PSNR improvement on each dataset while accurately capturing scene details. Furthermore, our method effectively preserves image details without requiring positional encoding, rendering a single scene in approximately 18 minutes on an NVIDIA RTX 3090 Ti GPU.

    Keywords: Scene representation, View synthesis, image-based rendering, volume rendering, 3D deep learning, Spectral bias

    Received: 11 Jan 2025; Accepted: 26 Mar 2025.

    Copyright: © 2025 Dai and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Shanqin Wang, Chuzhou Polytechnic, Chuzhou, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

    Research integrity at Frontiers

    Man ultramarathon runner in the mountains he trains at sunset

    94% of researchers rate our articles as excellent or good

    Learn more about the work of our research integrity team to safeguard the quality of each article we publish.


    Find out more