# Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering arXiv: https://arxiv.org/abs/2507.06103 ยท HTML: https://mlsanity.com/paper/2507.06103/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Builds on 29 of its 50 references that are in the map. - First posted on arXiv 8 Jul 2025. ## Builds on (most cited first, 29 of 29) - [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021) - [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020) - [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024) - [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021) - [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021) - [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023) - [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023) - [GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces](https://mlsanity.com/paper/2311.17977/) (2023) - [GS-IR: 3D Gaussian Splatting for Inverse Rendering](https://mlsanity.com/paper/2311.16473/) (2023) - [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021) - [NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)](https://mlsanity.com/paper/2210.00379/) (2022) - [3D-aware Image Synthesis via Learning Structural and Textural Representations](https://mlsanity.com/paper/2112.10759/) (2021) - [NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2203.11283/) (2022) - [GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction](https://mlsanity.com/paper/2403.16964/) (2024) - [Understanding SSIM](https://mlsanity.com/paper/2006.13846/) (2020) - [3D Gaussian Splatting with Deferred Reflection](https://mlsanity.com/paper/2404.18454/) (2024) - [Single Image Reflection Separation via Component Synergy](https://mlsanity.com/paper/2308.10027/) (2023) - [NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections](https://mlsanity.com/paper/2405.14871/) (2024) - [GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction](https://mlsanity.com/paper/2405.19671/) (2024) - [SpecNeRF: Gaussian Directional Encoding for Specular Reflections](https://mlsanity.com/paper/2312.13102/) (2023) - [Gaussian Splatting with NeRF-based Color and Opacity](https://mlsanity.com/paper/2312.13729/) (2023) - [Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracing](https://mlsanity.com/paper/2308.03280/) (2023) - [GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering](https://mlsanity.com/paper/2410.24204/) (2024) - [MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections](https://mlsanity.com/paper/2405.11921/) (2024) - [Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splatting](https://mlsanity.com/paper/2404.01168/) (2024) - [NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields](https://mlsanity.com/paper/2309.13039/) (2023) - [FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline](https://mlsanity.com/paper/2312.11537/) (2023) - [Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images](https://mlsanity.com/paper/2311.04521/) (2023) - [MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions](https://mlsanity.com/paper/2503.05182/) (2025) ## Built on by (most cited first, 4 of 4) - [Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting](https://mlsanity.com/paper/2606.05124/) (2026) - [Denoising-GS: Gaussian Splatting with Spatial-aware Denoising](https://mlsanity.com/paper/2605.14880/) (2026) - [Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction](https://mlsanity.com/paper/2608.06117/) (2026) - [STARS-GS: Structure-Aware Regularized Gaussian Splatting for Large-Scale Aerial Surface Reconstruction](https://mlsanity.com/paper/2609.03447/) (2026) ## Abstract (arXiv) Accurately rendering scenes with reflective surfaces remains a significant challenge in novel view synthesis, as existing methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) often misinterpret reflections as physical geometry, resulting in degraded reconstructions. Previous methods rely on incomplete and non-generalizable geometric constraints, leading to misalignment between the positions of Gaussian splats and the actual scene geometry. When dealing with real-world scenes containing complex geometry, the accumulation of Gaussians further exacerbates surface artifacts and results in blurred reconstructions. To address these limitations, in this work, we propose Ref-Unlock, a novel geometry-aware reflection modeling framework based on 3D Gaussian Splatting, which explicitly disentangles transmitted and reflected components to better capture complex reflections and enhance geometric consistency in real-world scenes. Our approach employs a dual-branch representation with high-order spherical harmonics to capture high-frequency reflective details, alongside a reflection removal module providing pseudo reflection-free supervision to guide clean decomposition. Additionally, we incorporate pseudo-depth maps and a geometry-aware bilateral smoothness constraint to enhance 3D geometric consistency and stability in decomposition. Extensive experiments demonstrate that Ref-Unlock significantly outperforms classical GS-based reflection methods and achieves competitive results with NeRF-based models, while enabling flexible vision foundation models (VFMs) driven reflection editing. Our method thus offers an efficient and generalizable solution for realistic rendering of reflective scenes. Our code is available at https://ref-unlock.github.io/.