test for kitti raw

[Ericgeese]

Hello, I am running this excellent project on kitti raw point cloud using provided pretrained model.
Strange hollows exisit in the upsampled clouds. Is it deal to cropping strategies or something else?
To reproduce:
bash test_realscan.sh pretrain/pu1k-punet ./data/real_scan_kitti_pugcn 0 --model punet --upsampler original bash test_realscan.sh pretrain/pu1k-mpu ./data/real_scan_kitti_pugcn 0 --model mpu --upsampler duplicate bash test_realscan.sh pretrain/pu1k-pugcn ./data/real_scan_kitti_pugcn 0 --model pugcn --k 20

using the 0th frame of 2011-09-26_0048 from kitti raw sequence.

Thank you!

[guochengqian]

thanks for your interest. I will investigate this issue after AAAI submission. My guess is the pretrained model is trained on PU-GCN with random sampling. You should used pretrained PU-GCN with uniform sampling on PUGAN’s date.

…

Sent from my iPhone On Aug 1, 2022, at 14:19, Gu Siyuan ***@***.***> wrote:  Hello, I am running this excellent project on kitti raw point cloud using provided pretrained model. Strange hollows exisit in the upsampled clouds. Is it deal to cropping strategies or something else? To reproduce: bash test_realscan.sh pretrain/pu1k-punet ./data/real_scan_kitti_pugcn 0 --model punet --upsampler original bash test_realscan.sh pretrain/pu1k-mpu ./data/real_scan_kitti_pugcn 0 --model mpu --upsampler duplicate bash test_realscan.sh pretrain/pu1k-pugcn ./data/real_scan_kitti_pugcn 0 --model pugcn --k 20 using the 0th frame of 2011-09-26_0048 from kitti raw sequence. [original]<https://user-images.githubusercontent.com/27678247/182136938-91709f4b-d597-436c-be06-4f06a7e1149f.png> [upsampling]<https://user-images.githubusercontent.com/27678247/182136956-ebf8f7c7-b0a7-4069-9a57-f4ff12b19fd0.png> Thank you! — Reply to this email directly, view it on GitHub<#14>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ALUHE2KOI2VVHJ37TD3VBFTVW6XDVANCNFSM55HF4NMA>. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[wangxianggang1997]

thanks for your interest. I will investigate this issue after AAAI submission. My guess is the pretrained model is trained on PU-GCN with random sampling. You should used pretrained PU-GCN with uniform sampling on PUGAN’s date.
…
Sent from my iPhone On Aug 1, 2022, at 14:19, Gu Siyuan @.> wrote:  Hello, I am running this excellent project on kitti raw point cloud using provided pretrained model. Strange hollows exisit in the upsampled clouds. Is it deal to cropping strategies or something else? To reproduce: bash test_realscan.sh pretrain/pu1k-punet ./data/real_scan_kitti_pugcn 0 --model punet --upsampler original bash test_realscan.sh pretrain/pu1k-mpu ./data/real_scan_kitti_pugcn 0 --model mpu --upsampler duplicate bash test_realscan.sh pretrain/pu1k-pugcn ./data/real_scan_kitti_pugcn 0 --model pugcn --k 20 using the 0th frame of 2011-09-26_0048 from kitti raw sequence. [original]https://user-images.githubusercontent.com/27678247/182136938-91709f4b-d597-436c-be06-4f06a7e1149f.png [upsampling]https://user-images.githubusercontent.com/27678247/182136956-ebf8f7c7-b0a7-4069-9a57-f4ff12b19fd0.png Thank you! — Reply to this email directly, view it on GitHub<#14>, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ALUHE2KOI2VVHJ37TD3VBFTVW6XDVANCNFSM55HF4NMA. You are receiving this because you are subscribed to this thread.Message ID: @.>

Thank you very much for your wonderful work, I am also testing the kitti data, and the same problem occurs, how to solve this problem?