HuangVictorAuto

@VisionaryMind , Hi, under what condition do you call your camera a fisheye camera? HOV>?. I am also trying to calibrate a HOV=120° camera, do i need to use a...

@VisionaryMind , thanks for your reply. you are right, we can walk around the probem by undistort the image first. after checking the code, i only found that it only...

Hey, Tianwei. You mean the target assignment here based on Openpcdet is slow and needs improments. Is the target assignment in your official repo also slow and need improvements?

@xiaokn , auto lidar2camera calibration, we have to prepare to mask the images, but when i setup the conda env as required and run the merge_mask.py, the program will be...

@jialeli1 @xuxiaoxxxx , Hi, guys, do you know the NLZ points of TOP lidar for object detection task is with semantic label or not ?

@laszloturanyi , i have the same issue above, after i add the line as you mentioned, a new problem come out. free(): invalid pointer. can you give me some advice?

@akjt , I meet the same issue, have you solved it ?

thansk for feedback. 1. I do check the final output differences for centerpoint model. It is OK. It is the same as my above comparision. conv_out indices is same, conv_out...

[scn_sch_onnx.zip](https://github.com/NVIDIA-AI-IOT/Lidar_AI_Solution/files/12721727/scn_sch_onnx.zip) scn_centerpoint_all.onnx is scn part for centerpoint model. scn_voxelnxet_all.onnx is scn part for voxelnext model. sch_voxelnext_all.onnx is sparse head part for voxelnext model. **you can pay attention to this onnx...

@hopef , sorry to bother, any updates on this issue?