# Deep Surface Light Fields

arXiv: https://arxiv.org/abs/1810.06514 · HTML: https://mlsanity.com/paper/1810.06514/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2018.

## Built on by (most cited first, 23 of 23)

- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [NeRF-Editing: Geometry Editing of Neural Radiance Fields](https://mlsanity.com/paper/2205.04978/) (2022)
- [CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image](https://mlsanity.com/paper/2502.12894/) (2025)
- [Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos](https://mlsanity.com/paper/2304.04452/) (2023)
- [Factor Fields: A Unified Framework for Neural Fields and Beyond](https://mlsanity.com/paper/2302.01226/) (2023)
- [Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis](https://mlsanity.com/paper/2402.12377/) (2024)
- [Ref-GS: Directional Factorization for 2D Gaussian Splatting](https://mlsanity.com/paper/2412.00905/) (2024)
- [VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams](https://mlsanity.com/paper/2312.01407/) (2023)
- [Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis](https://mlsanity.com/paper/2303.03808/) (2023)
- [Convolutional Neural Opacity Radiance Fields](https://mlsanity.com/paper/2104.01772/) (2021)
- [Hybrid Mesh-neural Representation for 3D Transparent Object Reconstruction](https://mlsanity.com/paper/2203.12613/) (2022)
- [When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering](https://mlsanity.com/paper/2504.17545/) (2025)
- [Neural Shell Texture Splatting: More Details and Fewer Primitives](https://mlsanity.com/paper/2507.20200/) (2025)
- [MirrorNeRF: One-shot Neural Portrait Radiance Field from Multi-mirror Catadioptric Imaging](https://mlsanity.com/paper/2104.02607/) (2021)
- [UC-NeRF: Uncertainty-aware Conditional Neural Radiance Fields from Endoscopic Sparse Views](https://mlsanity.com/paper/2409.02917/) (2024)
- [Deep Appearance Prefiltering](https://mlsanity.com/paper/2211.05932/) (2022)
- [Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstruction](https://mlsanity.com/paper/2501.11020/) (2025)
- [BG-Triangle: B'ezier Gaussian Triangle for 3D Vectorization and Rendering](https://mlsanity.com/paper/2503.13961/) (2025)
- [NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis](https://mlsanity.com/paper/2312.13328/) (2023)
- [NSLF-OL: Online Learning of Neural Surface Light Fields alongside Real-time Incremental 3D Reconstruction](https://mlsanity.com/paper/2305.00282/) (2023)
- [MiNL: Micro-images based Neural Representation for Light Fields](https://mlsanity.com/paper/2209.08277/) (2022)
- [NEPHELE: A Neural Platform for Highly Realistic Cloud Radiance Rendering](https://mlsanity.com/paper/2303.04086/) (2023)

## Abstract (arXiv)

A surface light field represents the radiance of rays originating from any points on the surface in any directions. Traditional approaches require ultra-dense sampling to ensure the rendering quality. In this paper, we present a novel neural network based technique called deep surface light field or DSLF to use only moderate sampling for high fidelity rendering. DSLF automatically fills in the missing data by leveraging different sampling patterns across the vertices and at the same time eliminates redundancies due to the network's prediction capability. For real data, we address the image registration problem as well as conduct texture-aware remeshing for aligning texture edges with vertices to avoid blurring. Comprehensive experiments show that DSLF can further achieve high data compression ratio while facilitating real-time rendering on the GPU.