iven-wu/casa

code for Category-agnostic Skeletal Animal Reconstruction

casa's Issues

.npz discrepancy test_animal

Hi,

I have an issue when running python main.py -c config/real_world.yaml
After running the clip_retrieve.py, the retrieval animal is correctly set.
However, after constructing the data_utils.Optimization_data() object, the .npz and .png files are loaded for the test_animal.
This is rather strange as we have as input of the test_animal the Annotations and JPEGImages from DAVIS, and thus no .npz files.

I'd hope to recieve clarification regarding this.

Thanks

Questions regarding the re-animation

Hi,

Thanks for the great work!

As described in the paper, the re-animation optimizes the joint angles of each bone for the skeletal shape, or the rigid transform for control point-based shape to minimize the Chamfer Distance between the reference shape and the predicted shape.

I was wondering how this is achieved for LASR and ViSER as these two methods rely on 2D observations (images, optical flow etc.) instead of directly optimizing to fit a target 3D shape. Could you provide more details on the procedure to do re-animation for LASR and ViSER in the paper? Thanks!