✳flâneur — a map of the web's best reading

3D Gaussian Splatting for Real-Time Radiance Field Rendering

repo-sam.inria.fr · 952 words · saved by 1 readers

Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (≥ 100 fps) novel-view synthesis at 1080p resolution. We tested our algorithm on a total of 13 real scenes taken from previously published datasets and the synthetic Blender dataset. In particular, we tested our approach on the full set of scenes presented in Mip-Nerf360 [Barron 2022], which is the current state of the art in NeRF rendering quality, two scenes from th

3D Gaussian Splatting for Real-Time Radiance Field Rendering 3D Gaussian Splatting for Real-Time Radiance Field Rendering SIGGRAPH 2023 (ACM Transactions on Graphics) Bernhard Kerbl * 1,2 Georgios Kopanas * 1,2 Thomas Leimkühler 3 George Drettakis 1,2 * Denotes equal contribution 1 Inria 2 Université Côte d'Azur 3 MPI Informatik 1 2 3 Paper - 115MB Paper - 25MB Code Scenes - 650MB Results - 7GB Group Publ. Page The geometry of catacaustics: (a) In the case of a planar reflector, a reflected point P results in a static virtual point p , independent of camera position c . (b) For curved reflecto

Explore this link on the map →

related reading