Zubair Irshad

Makes sense, thanks for the clarification. Maybe move them to their separate own thread titled 'Camera Pose optimization/Tracking' or a related name? I thought earlier about merging 6D object pose...

For a single object like [SRN dataset](https://github.com/vsitzmann/scene-representation-networks#data), yes this seems to be true (there are inverse to each other). For multi-object scenarios, the camera pose remains same but each object's...

Thanks for your interest in our work. To train CenterSnap on your own dataset, yes you need [latent embeddings](https://github.com/zubair-irshad/CenterSnap/blob/c2afd120428b0a07c88894da23311995b72bbbfd/prepare_data/generate_data_nocs.py#L202). We obtain them by pre-training an [auto-encoder](https://github.com/zubair-irshad/CenterSnap/blob/c2afd120428b0a07c88894da23311995b72bbbfd/external/shape_pretraining/train_ae.py) (Please see the snippet...

1. Yes, that's correct. We generate the GT latent embedding code by training an auto-encoder using the CAD models available in the training set (Please also see above response for...

@HannahHaensen, The CAD models used by NOCS are exactly similar to ShapeNet. The difference is, NOCS trains on only 6 Shapenet Categories and selects a subset of ShapeNet models for...


Awesome. Thanks @Berk035 May I ask what timestep and frame_skip values worked for you? Also what fps did you get after optimization?

Hi @ashwinram10 did you make progress with this issue ? I am also working on the same problem. Let me know if you want to discuss way forward for this...

@anoopsonar30 Did you find a work around this issue?

Thanks @anoopsonar30 Any chance you are getting the following error while running env = DroneNavigateEnv(config = args.config) within a loop (headless mode) **terminate called after throwing an instance of 'zmq::error_t'...