banmo
banmo copied to clipboard
BANMo Building Animatable 3D Neural Models from Many Casual Videos
Hello! I want to use Segment Anything Model to extract masks for cats or other animals. How should I change the code? I made some attempts myself and used SAM...
Thank you for your contribution! There seems to be an issue:
Hi, gangshan, many thanks for your awesome job! It's really amazing! May I ask how to render the colorful per-frame images like the picture below? ![2023-08-11 15-06-56 的屏幕截图](https://github.com/facebookresearch/banmo/assets/131245463/67046788-c526-4458-8a22-33a60beae8df) I run...
Thank you for bringing the fascinating work! I am trying it with CUDA 113, torch 1.10 and and met some problems: The situation arises when I tried to render novel...
Dear GengShan, Hi! Many thanks for your awesome job! I am trying to use your pre-optimized models for evaluation. `bash scripts/render_mgpu.sh 0 human-cap logdir/human-cap/human-cap.pth "0" 64 ` However, the results...
Hi, thank you for sharing your code. I have a question on the following line, correct_bones in the process of bone reinitialization. https://github.com/facebookresearch/banmo/blob/c4498030aeca9b056e700892788025a80953cb5a/nnutils/geom_utils.py#L698 Why do you correct bones using the...
Hi, I have a question about the following function, update_delta_rts. https://github.com/facebookresearch/banmo/blob/c4498030aeca9b056e700892788025a80953cb5a/nnutils/banmo.py#L1207 Why do you compute rays['bone_rts'] by multiplying (bone_rts_rst)^(-1) * bone_rts_fw in correct_rest_pose function? Is it right that you intend...
Hi Gengshan, Thanks for your great work! I have a couple of questions about the synthetic datasets (Eagle). - How to generate the 120 time-sequence obj from the one-instance model?...
Many thanks for your great job! Could you tell me how to generate dynamic 3d models like the "Articulated shape:" of cat-pikachiu on this [page](https://banmo-www.github.io/)?
Thanks for your great job. When I run your code to fit my video. there has some problem, in train_one_epoch() I debug it and find the bug happened when self._num_faces_per_mesh.unique()...