Mip-Splatting: Alias-Free 3D Gaussian Splatting

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 19447 - 19456
• Main Authors: Yu, Zehao, Chen, Anpei, Huang, Binbin, Sattler, Torsten, Geiger, Andreas
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.06.2024
• Subjects: 3D Reconstruction; Gaussian Splatting; Novel View Synthesis; Anti-aliasing; Real-time Rendering; Cameras; Computer vision; Matched filters; Rendering (computer graphics); Smoothing methods; Three-dimensional displays; Training
• ISSN: 1063-6919
• DOI: 10.1109/CVPR52733.2024.01839

Recently, 3D Gaussian Splatting has demonstrated impressive novel view synthesis results, reaching high fidelity and efficiency. However, strong artifacts can be observed when changing the sampling rate, e.g., by changing focal length or camera distance. We find that the source for this phenomenon can be attributed to the lack of 3D frequency constraints and the usage of a 2D dilation filter. To address this problem, we introduce a 3D smoothing filter to constrains the size of the 3D Gaussian primitives based on the maximal sampling frequency induced by the input views. It eliminates high-frequency artifacts when zooming in. Moreover, replacing 2D dilation with a 2D Mip filter, which simulates a 2D box filter, effectively mitigates aliasing and dilation issues. Our evaluation, including scenarios such a training on single-scale images and testing on multiple scales, validates the effectiveness of our approach.