RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting
Not on the map. Why?
Abstract (arXiv)
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis with high visual quality. However, existing methods struggle with semi-transparent specular surfaces that exhibit both complex reflections and clear transmission, often producing blurry reflections or overly occluded transmission. To address this, we present RT-Splatting, a framework that disentangles each Gaussian's geometric occupancy from its optical opacity. This factorization yields a unified surface-volume scene representation with a single set of Gaussian primitives. Our hybrid renderer interprets this representation both as a surface to capture high-frequency reflections and as a volume to preserve clear transmission. To mitigate the ambiguity in jointly optimizing reflection and transmission, we introduce Specular-Aware Gradient Gating, which suppresses misleading gradients from highly specular regions into the transmission branch, effectively reducing distracting floaters. Experiments on challenging semi-transparent scenes show that RT-Splatting achieves state-of-the-art performance, delivering high-fidelity reflections and clear transmission with real-time rendering. Moreover, our factorization naturally enables flexible scene editing. The project page is available at https://sjj118.github.io/RT-Splatting.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 51 references that are in the map. First posted on arXiv 18 May 2026.
Builds on
40 of 51 references.
References · 40
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2023Segment Anythingcited by 8,158
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
- 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
- 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 249
- 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 220
- 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
- 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 138
28 more
- 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 121
- 2021Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objectscited by 119
- 2023GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorizationcited by 86
- 2023Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflectioncited by 68
- 2023ENVIDR: Implicit Differentiable Renderer with Neural Environment Lightingcited by 63
- 2024DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shadingcited by 40
- 2024GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Renderingcited by 39
- 2024Reflective Gaussian Splattingcited by 39
- 2023Neural Microfacet Fields for Inverse Renderingcited by 37
- 2024EnvGS: Modeling View-Dependent Appearance with Environment Gaussiancited by 34
- 2024NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflectionscited by 32
- 2022Eikonal Fields for Refractive Novel-View Synthesiscited by 30
- 2023SpecNeRF: Gaussian Directional Encoding for Specular Reflectionscited by 30
- 2023UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflectionscited by 29
- 2024Ref-GS: Directional Factorization for 2D Gaussian Splattingcited by 27
- 2024GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Renderingcited by 22
- 2024PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relightingcited by 17
- 2023NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fieldscited by 16
- 2025TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussianscited by 16
- 2023NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objectscited by 14
- 2024GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priorscited by 14
- 2025TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priorscited by 14
- 2024GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstructioncited by 10
- 2024Planar Reflection-Aware Neural Radiance Fieldscited by 6
- 2024Progressive Radiance Distillation for Inverse Rendering with Gaussian Splattingcited by 5
- 2024RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Renderingcited by 3
- 2023REF2-NeRF: Reflection and Refraction aware Neural Radiance Fieldcited by 2
- 2025Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenescited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.