This is an implementation of the keypoint network proposed in "Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning [pdf]". Given a single 2D image of a known class, this network can predict a set of 3D keypoints that are consistent across viewing angles of the same object and across object instances. These keypoints and their detectors are discovered and learned automatically without keypoint location supervision [demo].
Apache License 2.0
9
stars
3
forks
source link
The predictions of chairs vary widely from the result in the paper. #1
Hi, thanks for your sharing.
I got the trained model of chairs by running the following cmd:
python main.py --model_dir=/home/user1/code/keypoint-network/keypointnet_trained_model_chair --dset=/home/user1/code/keypoint-network/chairs_with_keypoints/
however, the predict kpts seem meaningless. Could you help me to find out what the problem is?
Hi, thanks for your sharing. I got the trained model of chairs by running the following cmd: python main.py --model_dir=/home/user1/code/keypoint-network/keypointnet_trained_model_chair --dset=/home/user1/code/keypoint-network/chairs_with_keypoints/
however, the predict kpts seem meaningless. Could you help me to find out what the problem is?