Open duckduck-sys opened 3 years ago
@duckduck-sys I think there are two points to note about the data:
@duckduck-sys I think there are two points to note about the data:
- location: the neck should be halfway between the shoulders, and the thorax should be roughly halfway between the neck and the hips.
- scale: normalization depends on the image width(mapping to [-1,1] based on the w), thus, the proportion of human body in the image needs to match H36M.
- raw output
- after scaling the locations
- after modifying the location of the neck and the thorax
hi, how do you calculate the spine point
hi @duckduck-sys 大神,你的数据归一化后有点奇怪,还有我想请教下您现在能正确回归出3d pose了吗,主要是hip和spine节点我不懂计算,还有就是hip节点要假定为(0,0)吗
@develduan Hi Duan, can you share this solution? I'm also facing somewhat same problem. Thanks
@develduan Hi. I also face the same problem about how to figure out the spine point, because the stack-hourglass doesn't output the spine point
@lisa676 @dandingol03 Hi, I'm sorry that I stopped following this project because it didn't work very well on my dataset(the wild environment). In my dataset, all pedestrians stand upright, so I simply treated the midpoint of the neck and the pelvis as the thorax/spine: positions_mpii[i_thorax] = (positions_mpii[i_neck] + positions_mpii[i_pelvis]) / 2
. After normalize_screen_coordinates
, scale the locations with a factor to fit the proportion of human body in the image of H36M, in my case: positions = positions / 2
.
In my case, I want to get the 3D posture directly from the image instead of getting a 2D posture and then a 3D posture, and I got a better result by following this paper "Angjoo Kanazawa, Michael J. Black, David W. Jacobs, Jitendra Malik. End-to-end Recovery of Human Shape and Pose".
@develduan Firstly, thanks for your kindly apply. Secondly, the paper " End-to-end Recovery of Human Shape and Pose" is cool, i will delve into the paper soon. And last, here is my email dandingol03@outlook.com, maybe someday we can exchange idea about 3d pose estimation~
Inference on images in the wild using SemGCN has been partially covered in this thread and others, but only the overall process has been made clear. I.e.:
Below i will follow each step, using the test image of size 300x600 to the left.
For Step 1, i use EfficientPose to generate the MPII format 2d pose of the test image as shown above on the right, here's the numeric output:
For Step 2, i run this:
positions = positions[:, SH_TO_GT_PERM, :]
To get the output:
For Step 3, i run this:
positions[..., :2] = normalize_screen_coordinates(positions[..., :2], w=300, h=600)
To get the output:
For Step 4, the above is used as input to the SemGCN SH model running this:
Which gives the output:
When visualized this looks completely wrong... See image below. Can anyone highlight on where the problem lies? Is it a problem with the pre-processing, or with the model?