Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/ViTMatte

ViTMatte

Reported on 8 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

Image MattingonDistinctions-646
MSE· 2023-05-24
0.0015
SOTA
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers arXiv:2305.15272
Image MattingonDistinctions-646
Conn· 2023-05-24
12.95
best: 40.56 (PP-Matting)
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers arXiv:2305.15272
Image MattingonDistinctions-646
Grad· 2023-05-24
7.03
best: 43.91 (PP-Matting)
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers arXiv:2305.15272
Image MattingonDistinctions-646
SAD· 2023-05-24
17.05
best: 40.69 (PP-Matting)
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers arXiv:2305.15272
Image MattingonComposition-1K
Conn· 2023-05-24
14.78
best: 50.8 (DIM)
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers arXiv:2305.15272
Image MattingonComposition-1K
Grad· 2023-05-24
6.74
best: 31 (DIM)
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers arXiv:2305.15272
Image MattingonComposition-1K
MSE· 2023-05-24
3
best: 2.26 (DiffMatte)
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers arXiv:2305.15272
Image MattingonComposition-1K
SAD· 2023-05-24
20.33
best: 46.22 (PP-Matting)
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers arXiv:2305.15272