adafuse-3d-human-pose
adafuse-3d-human-pose copied to clipboard
zhezh
[IJCV-2020] AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
hello, I have several cameras. the number and position are quite different from human3.6m. How should I get the prediction by using multi-camera data?
Hello. First of all, thank you for sharing the results of the good research. I leave a post because I have a few questions. First, do you have any plans...
hi,i am newbie.I would like to ask why it can adapt to any number of cameras？ If you train the weights from 4 views,but I need 6 views to test....
Hello, I wanted to ask in what unit the OcclusionPerson dataset provides 3D ground truth? Meters or millimeters? Thank you!
I configured the occlusion_person_dataset as instructed, but when I run `python run/adafuse/adafuse_main.py --cfg experiments/occlusion_person/occlusion_person_8view.yaml --evaluate true` It will have an error: `cv2.error: OpenCV(3.4.2) /io/opencv/modules/imgproc/src/imgwarp.cpp:2610: error: (-215:Assertion failed) src.cols > 0...
the `epipolar_fusion_layer.py` works fine for the heatmap which width and height are the same, but for the CMU panoptic dataset I get the heatmap of 240X128, so I got error...
