v0.0.3
ShenhanQian/VHAPv0.0.3Mar 7, 2025by ShenhanQian
AI Summary
This release adds support for cameras whose principal points are not at the image center, simplifies rendering functions to allow FlameViewer to load texture maps, and introduces a temporal smoothness term for expression with refactored loss names.
Key Highlights
- Support for cameras with principal points not at image center
- Simplified rendering functions
- FlameViewer can now load texture maps
- Added temporal smoothness term for expression
- Refactored and simplified loss names
New Features
- Camera principal point offset support
- Texture map loading in FlameViewer
- Temporal smoothness for expression
- Refactored loss naming
Full Release Notes
**Major changes:** - Support cameras whose principal points are not at the image center. (https://github.com/ShenhanQian/VHAP/commit/34afb35bfe71a8b31d4a95fa41ef9b625bc1fc24) - Simplify rendering functions and allow FlameViewer to load a texture map. (https://github.com/ShenhanQian/VHAP/commit/d8ce4e97a38c85bb22cfee5dacced09d51723b36) - Add temporal smoothness term for the expression. Refract and simplify loss names. (https://github.com/ShenhanQian/VHAP/commit/1603303eb8c60bab3a8d8f47c03386f8dfffa04b)