| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://vllab.github.io/EigenGS/
access-control-allow-origin: *
expires: Mon, 29 Dec 2025 04:23:01 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: 34CB:444BC:849A4F:94FB9D:6951FFCD
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 04:13:01 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210064-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766981582.612427,VS0,VE210
vary: Accept-Encoding
x-fastly-request-id: 73d095e49a054626e65c94461488c445331c1a6d
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Thu, 05 Jun 2025 08:56:09 GMT
access-control-allow-origin: *
etag: W/"68415ba9-1d78"
expires: Mon, 29 Dec 2025 04:23:01 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: CBFB:1F53DD:840DD1:946FF8:6951FFCD
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 04:13:02 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210064-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766981582.841786,VS0,VE212
vary: Accept-Encoding
x-fastly-request-id: 73698703856c4865842f3f36ae41dc28874f389f
content-length: 2497
EigenGS Representation: From Eigenspace to Gaussian Image Space
EigenGS Representation: From Eigenspace to Gaussian Image Space
Fast convergence speed on Cats dataset. Our method achieves perceptually significant improvements within the first 100 iterations. The rapid visual convergence demonstrates the effectiveness of our PCA-based initialization, particularly on well-aligned datasets with moderate resolution. Additionally, our result also indicates that traditional PCA reconstruction, which is basically similar to our result at iteration zero, can be further improved by our approach.
EigenGS Representation:
From Eigenspace to Gaussian Image Space
CVPR 2025
- Lo-Wei Tai1
- Ching-En Li1
- Cheng-Lin Chen1
- Chih-Jung Tsai1
- Hwann-Tzong Chen1
- Tyng-Luh Liu2
- 1National Tsing Hua University
- 2Academia Sinica
Abstract
Principal Component Analysis (PCA), a classical dimensionality reduction technique, and 2D Gaussian representation, an adaptation of 3D Gaussian Splatting for image representation, offer distinct approaches to modeling visual data. We present EigenGS, a novel method that bridges these paradigms through an efficient transformation pipeline connecting eigenspace and image-space Gaussian representations. Our approach enables instant initialization of Gaussian parameters for new images without requiring per-image optimization from scratch, dramatically accelerating convergence. EigenGS introduces a frequency-aware learning mechanism that encourages Gaussians to adapt to different scales, effectively modeling varied spatial frequencies and preventing artifacts in high-resolution reconstruction. Extensive experiments demonstrate that EigenGS not only achieves superior reconstruction quality compared to direct 2D Gaussian fitting but also reduces the necessary parameter count and training time. The results highlight EigenGS's effectiveness and generalization ability across images with varying resolutions and diverse categories, making Gaussian-based image representation both high-quality and viable for real-time applications.
Better Initialization and Faster Convergence