Min
Max
Min
Max
Min
Max
Min
Max
Top Paper Computer Vision Models
The models below have been fine-tuned for various paper detection tasks. You can try out each model in your browser, or test an edge deployment solution (i.e. to an NVIDIA Jetson). You can use the datasets associated with the models below as a starting point for building your own paper detection model.
At the bottom of this page, we have guides on how to count papers in images and videos.
2.2k images 10 classes 2 models
8.5k images 6 classes 1 model
425 images 13 classes 2 models
4.7k images 19 classes 2 models
497 images 13 classes 1 model
6.1k images 6 classes 4 models
6.3k images 6 classes 2 models
6.1k images 6 classes 1 model
3.3k images 16 classes 2 models
3.8k images 10 classes 1 model
2.1k images 10 classes 2 models
524 images 17 classes 1 model
400 images 6 classes 1 model
591 images 101 classes 1 model
Bacchus Decaffeinated Bear's Original nacho Cantata Sweet Americano Can Carbo Fire Chicken Stir-Fried Noodles Cass Whal Myung Su Chapagetti Big Bowl Noodles Cheongha dark blue Cheongha sky blue Chocoemon drink ice Fresh Udon Noodles Fresh and Sweet Yogeolli Gatorade Lemon Flavor Guinness extra stout dark lively Hite Extra Cold Can Hot Chicken Fried Noodles Jalapeno Cheese Kirin Ichiban Large Cup of Stir-Fried Gan Jjambbong Lotte Chilsung Cider Can Lotte Watermelon Bar Ade Master Vanilla Black Pet
358 images 15 classes 2 models
4.6k images 6 classes 1 model
5.1k images 17 classes 2 models
4.3k images 12 classes 1 model
2.4k images 15 classes 1 model
7.1k images 66 classes 1 model
7.8k images 6 classes 3 models
1.1k images 5 classes 1 model
6k images 12 classes 1 model