paTRICK-swk/D3DP
[ICCV2023] The PyTorch implementation for "Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation"
PythonMIT
Issues
- 2
- 1
training loss setting
#26 opened by rabbitchenrui - 2
test_result when gt_2d as input
#27 opened by rabbitchenrui - 0
cuda empty cache
#25 opened by bruceZHU08 - 4
About the best results
#4 opened by jiejie22333 - 2
- 0
Apply D3DP on animal
#24 opened by Batwho - 0
Single-frame estimation?
#23 opened by taeyunwoo - 3
About the reverse process
#6 opened by WilliammmZ - 1
single-step denoising
#18 opened by zhenhuat - 0
training loss
#21 opened by harryzhangOG - 0
ALphapose 2D estimator
#19 opened by UsamaShaikh1 - 0
evaluate pre-trained(H36M) model on 3DHP
#17 opened by youpJiang - 0
training time
#16 opened by luckyday2022 - 0
Question about Reimplementation of MixSTE
#15 opened by Brian417-cup - 0
Evaluation of on the wild videos
#14 opened by anas-zafar - 0
- 1
Inference on in the wild videos
#12 opened by UsamaShaikh1 - 3
where is the model.py file??
#10 opened by hotelbread - 1
training evaluation CUDA out of memory
#9 opened by HarrytheOrange - 3
- 4
Question about the paper
#11 opened by Andyen512 - 0
- 3
Clarification for using in the wild
#3 opened by vv111y - 1
Some codes can't be found
#1 opened by dnqf11 - 1
- 4
bug for rearrange
#2 opened by zhLawliet