Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting

About

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.

Ji Shi, Xianghua Ying, Bowei Xing, Ruohao Guo, Wenzhen Yue• 2026

Related benchmarks

TaskDatasetResultRank
Novel View Synthesisself-captured dataset
Mean PSNR28.78
10
Novel View SynthesisPublic Scenes (Ref-Real, NeRF-Casting, EnvGS, T&T) Entire Image (test)
PSNR27.49
7
Novel View SynthesisPublic Scenes Ref-Real, NeRF-Casting, EnvGS, T&T - Transparent Region (test)
PSNR39.765
7
Novel View Synthesisself-captured scenes (Transparent region)
PSNR35.49
7
Showing 4 of 4 rows

Other info

GitHub

Follow for update