Fix False Transparency by Noise Guided Splatting
–Neural Information Processing Systems
Opaque objects reconstructed by 3DGaussian Splatting (3DGS) often exhibit a falsely transparent surface, leading to inconsistent background and internal patterns under camera motion in interactive viewing. This issue stems from the ill-posed optimization in 3DGS. During training, background and foreground Gaussians are blended via α-compositing and optimized solely against the input RGB images using a photometric loss. As this process lacks an explicit constraint on surface opacity, the optimization may incorrectly assign transparency to opaque regions, resulting in view-inconsistent and falsely transparent output. This issue is difficult to detect in standard evaluation settings (i.e., rendering static images), but becomes particularly evident in object-centric reconstructions under interactive viewing.
Neural Information Processing Systems
Jun-23-2026, 03:37:58 GMT
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (0.93)
- Research Report
- Industry:
- Media
- Television (0.34)
- Photography (0.34)
- Film (0.34)
- Media
- Technology:
- Information Technology
- Graphics (0.87)
- Artificial Intelligence
- Vision (1.00)
- Machine Learning (1.00)
- Representation & Reasoning (0.68)
- Robots (0.67)
- Information Technology