tomasjakab/imm
Code for unsupervised learning of object landmarks as proposed in "Unsupervised Learning of Object Landmarks through Conditional Image Generation", Tomas Jakab*, Ankush Gupta*, Hakan Bilen, Andrea Vedaldi, Advances in Neural Information Processing Systems (NeurIPS) 2018.
Python
Issues
- 0
keypoint outside -1..+1 ?
#19 opened by iperov - 0
Pretrained model trained 4 points
#18 opened by wsunid - 0
Images
#17 opened by NorthTree-BeiLin - 3
The "Download trained model" link is not working, can you please provide a working url for the checkpoints?
#16 opened by rahulrahaman - 1
Can this work handle occlusion?
#15 opened by towardsautonomy - 0
- 0
Loss statistics
#13 opened by NiteshBharadwaj - 0
- 0
Training with Custom Dataset
#11 opened by stat2008 - 0
Some questions about loss network.
#10 opened by HuAndrew - 1
can you provide a checkpoint getting from training on human body dataset for me to do fine-tune?
#9 opened by qdmy - 2
Some questions about the ws value?
#8 opened by HuAndrew - 4
- 1
Model for Human 3.6M dataset
#6 opened by anuragdmadan - 0
- 1
Video Dataset
#4 opened by theRealSuperMario - 3
Disentangling style and geometry
#3 opened by abcp4 - 2
Some questions about the code
#2 opened by NolenChen - 2
Expected training time
#1 opened by chenhsuanlin