Cristian Chivriga

Results 6 comments of Cristian Chivriga

For anyone that is stuck, use the modified version that may help much: [Inference.py](https://github.com/DeepMotionAIResearch/DenseASPP/blob/35a3e05fd70398b740776fa3ff1378c8470b6026/inference.py#L120) with the (basically a few remapping is needed for the weight state), and don't forget to...

Hi, you can use `tensorboard --logdir logs/... --port 6006` and visualize the progressive refinement of the voxel grid. We actually took the sample pictures based on the state of the...

@YoYooX It actually has the color but only per-vertex not per face. Maybe that's the reason why the 3D viewer is failing to properly render it (tested with meshlab). Can...

Is this going to be merged? @geocine Wondering what's the performance like - input token size roughly per image - patching size.