Table 2: Designers’ rating of edge realism and artifact absence.
Table 1: Average metrics over AIM-500 dataset. Bold = best.
Single GPU, version v1.2 of AIarty Matting, no trimap support (AIarty does not accept trimaps). Future work should test on video sequences and VR applications. References [1] Qin, X., et al. (2020). U²-Net: Going deeper with nested U-structure for salient object detection. Pattern Recognition , 106, 107404. aiarty matting
Image matting, generative AI, alpha matte, edge detection, AIarty 1. Introduction Image matting is essential for photo editing, film compositing, and augmented reality. Traditional methods (e.g., GrabCut, Closed-Form Matting) require user-supplied trimaps or scribbles. Recent deep learning approaches have enabled automatic matting, but they struggle with complex boundaries or low-contrast regions.
[3] Sengupta, S., et al. (2020). Background matting v2. CVPR . Table 2: Designers’ rating of edge realism and
AIarty Matting achieves the lowest SAD and gradient error, indicating superior edge fidelity. However, it is 1.8× slower than MODNet. | Method | Mean score (1–5) | Std Dev | |-------------------|------------------|---------| | MODNet | 2.9 | 0.8 | | Adobe Photoshop | 3.7 | 0.6 | | U²-Net | 3.9 | 0.5 | | AIarty Matting | 4.5 | 0.4 |
[5] AIM-500 Dataset. [Your institution’s repository link]. Appendix A – Sample images and alpha mattes (available online). Appendix B – Full SAD scores per image category. Appendix C – Statistical significance tests (ANOVA). If AIarty Matting is a real, specific product, replace the hypothetical architecture and dataset with actual specifications, and conduct a proper benchmark. The above structure serves as a template for any AI matting tool evaluation paper. Single GPU, version v1
[2] Ke, Z., et al. (2020). MODNet: Real-time trimap-free portrait matting via objective decomposition. AAAI .