| | 194 | == Implement the eSSIM metric == |
| | 195 | |
| | 196 | '''Description:''' eSSIM is an evolution of SSIM which improves correlation with subjective scores by employing Minkowski pooling and reduces complexity by employing box filters and striding. |
| | 197 | The original algorithm is described here https://ieeexplore.ieee.org/document/9344648 |
| | 198 | There is an implementation of that with further optimizations here https://github.com/facebookresearch/essim |
| | 199 | |
| | 200 | |
| | 201 | '''Expected results:''' Implement the eSSIM metric by extending the existing SSIM filter or into a new filter. |
| | 202 | |
| | 203 | '''Prerequisites:''' Good C code, basic familiarity with Git, and basic knowledge of image processing. |
| | 204 | |
| | 205 | '''Difficulty:''' Medium to Hard |
| | 206 | |
| | 207 | '''Qualification Task:''' Fix a random bug in an existing filter. |
| | 208 | |
| | 209 | '''Mentor:''' TBD |
| | 210 | |
| | 211 | '''Backup Mentor:''' thilo.borgmann at mail dot de |
| | 212 | |
| | 213 | '''Duration:''' TBD |
| | 214 | |
| | 215 | |
| | 216 | |
