Closed dingjiansw101 closed 8 months ago
Hi, thank you for your interest in our work. In these 3D-VL tasks evaluation, there are two settings, results using ground-truth mask and results using predicted mask. On benchmarks like Sr3D, Nr3D, you should use gt mask for evaluation. On benchmarks like ScanRefer, ScanQA, Scan2Cap, SQA3D, you should set pc_type to pred.
Best, Ziyu
Hi Ziyu,
Thanks for your reply. However, I found that the pc_type is set to "gt" during training and testing in the "ScanQA" task.
Best, Jian Ding
Yes, setting pc_type to "gt" will make testing faster(for checking model performance only). If you want to submit the result to benchmark, you should change it to "pred" for comparison with other paper.
Best, Ziyu
Are the data for pc_type "pred" read from the path "./data/scanfamily/save_mask"? How to generate such files? Are they predicted by 3dvista or other models?
Best, Jian Ding
They are predicted by mask3d segmentation model. These masks can be found in this issue #12.
Best, Ziyu
Thanks for the reply. Have you fine-tuned the mask3d according to the labels of scanqa, or just used the pretrained mask3d model?
Best, Jian Ding
An additional question, have you evaluated on the task "Object localization performance on the ScanQA dataset"?
Hi
Best, Ziyu
Hi Ziyu, Thanks for your reply. I still have a few questions since I am new to this area.
Hi
Best, Ziyu
Dear Authors,
I am confused about the pc_type. When will you set the pc_type as "pred"?
Best, Jian Ding