Chenhang He

Results 4 issues of Chenhang He

I saw from your implementation the point cloud are from LiDAR, however in your paper you mentioned the point cloud is generated from depth image? Am I misunderstood something?

Hi, I use your pre-trained model and convert the disp to depth with the following formula, Depth = f * baseline / pred_disp, where the f and baseline are directly...

Hi, Thanks for sharing this great work. I train on train(3712) and evaluate on the val (3769) can only gain very low AP. Could you share your training log file...

Hi, Thanks for sharing the codes! I notice the number of training samples in your train_annotations.json is only 3622 while the original one has 3712 samples. Could you please provide...