TL;DR
This paper introduces a deferred shading technique for Gaussian splatting that effectively renders specular reflections, improving visual quality and normal estimation in novel view synthesis without sacrificing rendering speed.
Contribution
It proposes a novel deferred shading method that enhances specular reflection rendering in Gaussian radiance fields by leveraging reflection gradients for better normal estimation.
Findings
Outperforms state-of-the-art methods in specular reflection synthesis
Achieves higher PSNR on synthetic and real scenes
Maintains real-time rendering speeds
Abstract
The advent of neural and Gaussian-based radiance field methods have achieved great success in the field of novel view synthesis. However, specular reflection remains non-trivial, as the high frequency radiance field is notoriously difficult to fit stably and accurately. We present a deferred shading method to effectively render specular reflection with Gaussian splatting. The key challenge comes from the environment map reflection model, which requires accurate surface normal while simultaneously bottlenecks normal estimation with discontinuous gradients. We leverage the per-pixel reflection gradients generated by deferred shading to bridge the optimization process of neighboring Gaussians, allowing nearly correct normal estimations to gradually propagate and eventually spread over all reflective objects. Our method significantly outperforms state-of-the-art techniques and concurrent…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
