qsisi
qsisi
Hello! It seems a bit confusing to me about the actual differences in between the **TensorField** and the **SparseTensor**, could someone help me with it? Thanks!
Hello! Thanks for sharing this excellent work, by the way, which software of tool did you use to obtain the visualization result between **4:21~4:40** in your full CVPR oral presentation...
Hello! I have two questions: 1. As far as I can see, the current released version doesn't support Multi-GPU implementation, the hyper-params are set clearly for Multi-GPU (train_batch_size is set...
Hello! Thanks for open-sourcing this work. When I run: `python train_synthetic_data.py --load_folder scripts/synthetic_data/line_pole_noise/` The observation is that the GPU is not actually used (only 300~MB occupied), but the CPU-util increases...
Hello! I got a question about the inlier loss as defined in equation-11 in the paper. In my understanding, the definition of inlier loss in the paper is to average...
Hello! Thank you for open-sourcing this impressive work, I have several questions: 1. Could you provide the DCP_v2 checkpoints? I trained the DCP for 250 epochs (noise-free, 5112/1266 pairs for...
Hello! Thanks for open-sourcing this amazing work. Here I got a question about the EMD loss. My intention is to understand the exact way of the computation for the EMD...
Hello. https://github.com/acschaefer/polex/blob/1d1d1819578079c5d4ce05b5db2584d4f52ac864/poles/poles.py#L93-L93 This is a shallow copy of numpy array, but the code seems to need the deep copy of optcentroids[ic] -> lastcentroid, so does this need to be modified?...
Hello! Thanks for open-sourcing this amazing work! Here I have some questions about the paper. 1. I wonder how to get the actual U^T@U given the ground-truth rotation and translation...