RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Rendering
Not on the map. Why?
Abstract (arXiv)
3D Gaussian Splatting (3D-GS) has made a notable advancement in the field of neural rendering, 3D scene reconstruction, and novel view synthesis. Nevertheless, 3D-GS encounters the main challenge when it comes to accurately representing physical reflections, especially in the case of total reflection and semi-reflection that are commonly found in real-world scenes. This limitation causes reflections to be mistakenly treated as independent elements with physical presence, leading to imprecise reconstructions. Herein, to tackle this challenge, we propose RefGaussian to disentangle reflections from 3D-GS for realistically modeling reflections. Specifically, we propose to split a scene into transmitted and reflected components and represent these components using two Spherical Harmonics (SH). Given that this decomposition is not fully determined, we employ local regularization techniques to ensure local smoothness for both the transmitted and reflected components, thereby achieving more plausible decomposition outcomes than 3D-GS. Experimental results demonstrate that our approach achieves superior novel view synthesis and accurate depth estimation outcomes. Furthermore, it enables the utilization of scene editing applications, ensuring both high-quality results and physical coherence.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 9 Jun 2024.
Builds on
29 of 39 references.
References · 29
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
- 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
- 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
- 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
17 more
- 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
- 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 249
- 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
- 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
- 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
- 2021Point-Based Neural Rendering with Per-View Optimizationcited by 188
- 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
- 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 138
- 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 121
- 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
- 20243D Gaussian as a New Era: A Surveycited by 102
- 2023SpecNeRF: Gaussian Directional Encoding for Specular Reflectionscited by 30
- 2023Gaussian Splatting with NeRF-based Color and Opacitycited by 30
- 2023Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracingcited by 22
- 2024MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflectionscited by 21
- 2024Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splattingcited by 18
- 2023TraM-NeRF: Tracing Mirror and Near-Perfect Specular Reflections through Neural Radiance Fieldscited by 7
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.