The parallel implementation of Sparse 3D Transform-Domain Collaborative filter (BM3D). The parallization is based on OpenMP and OpenMP SIMD. This implementation is more efficient than Dabov or Lebrun implementation (2560×1440 – used memory: Lebrun – 13.5GB, Ours – 330 MB, 7680×4320: Lebrun – 101GB, Ours – 2.1GB).
Run Blender with BM3D filter
- GCC 6.3.0
- other external libraries are included
- run_blender.sh – run Blender
source code: Blender Patch D2649
Blender uses the GNU General Public License, which describes the rights to distribute or change the code.