GlassSplat: Geometric Consistency and Pruning for Reflection-Free 3D Scene Reconstruction
Open Access
- 15 June 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1423-1431
Abstract
Rendering high-fidelity 3D scenes is crucial for immersive applications like virtual reality and digital twins. However, standard 3D Gaussian Splatting (3DGS) relies heavily on multi-view consistency, making it fragile in real-world scenarios plagued by glass reflections. These reflections often manifest as geometric "floaters" or severe texture artifacts, obscuring the true background. Existing solutions, which typically employ single-image priors or NeRF-based in-painting, often lack explicit 3D constraints or rely on synthetic data, failing to generalize to complex environments. To address these challenges, we first present a novel benchmark dataset of 8 real-world scenes, capturing physically paired reflective and reflection-free images. Building on this, we propose GlassSplat, a robust framework designed to eliminate view-dependent artifacts and recover clean transmission geometry. Our method initializes with a reflection prior and introduces an Affine-Based Exposure Correction module to align global photometric inconsistencies. To distinguishing valid geometry from virtual outliers, we incorporate an Epipolar Consistency Loss and an uncertainty-weighted Depth Regularization. Finally, to physically purge residual noise, we devise a Visibility-Aware Pruning strategy that dynamically filters artifacts based on multi-view statistics. Extensive experiments demonstrate that GlassSplat significantly outperforms state-of-the-art approaches, effectively recovering a clean, artifact-free 3D scene representation.Keywords
This publication has 31 references indexed in Scilit:
- Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes2025
- PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics2024
- Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis2024
- Single Image Reflection Removal Through Cascaded Refinement2020
- Fast Single Image Reflection Suppression via Convex Optimization2019
- Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements2019
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Single Image Reflection Separation with Perceptual Losses2018
- CRRN: Multi-scale Guided Concurrent Reflection Removal Network2018
- Single Image Reflection Suppression2017