search

Nightmare-n / UniPAD

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving (CVPR 2024)
https://arxiv.org/abs/2310.08370
Apache License 2.0
150 stars 5 forks source link

About rendering #3

Closed Doctor-James closed 7 months ago

Doctor-James commented 8 months ago

Thank you for your work. I would like to ask how sampling 512 rays per image view achieves such a high rendering resolution in the final render image(figure3 in your paper). For a high-definition image of 1600 900, 512 seems like a very small number.

Nightmare-n commented 8 months ago

Hi, thanks for your interest! During training, we only sample 512 rays for supervision. During inference (visualization), all 1600 * 900 rays are used to render the image.