Image-GS: Content-Adaptive Image Representation via 2D Gaussians
a day ago
- #Graphics
- #Image Representation
- #2D Gaussians
- Introduction of Image-GS, a content-adaptive image representation based on 2D Gaussians.
- Achieves balance between visual fidelity and memory efficiency for stylized images.
- Supports hardware-friendly rapid random access, requiring only 0.3K MACs per pixel.
- Features error-guided progressive optimization for a smooth level-of-detail hierarchy.
- Demonstrated applications include texture compression, semantics-aware compression, and joint image compression and restoration.
- Detailed setup instructions for Python environment and dependencies.
- Steps for optimizing and rendering Image-GS representations with various configurations.
- Options for bit precision control, logging, and input image handling.
- Acknowledgments to contributors and licensing under MIT.
- Citation information for referencing the work.