zhangyp15 / OccFormer

[ICCV 2023] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
https://arxiv.org/abs/2304.05316
Apache License 2.0
324 stars 22 forks source link

How generate the occupancy label visualization? #3

Closed rockywind closed 1 year ago

rockywind commented 1 year ago

Hi, Thank you for sharing the great work! I want to visualize the occupancy label like the demo. But I don't know how to do it. Can you help me?

zhangyp15 commented 1 year ago

Hi, thanks for your interest. I think the easiest way is to modify from the test-function by the following: (1) simply browse the dataloder to get the images and ground-truth occupancy labels (2) replace the output_voxels into the function save_output_semantic_kitti by the gt_occupancy from the dataloader.

Then you can visualize the saved files following the demo pipeline.