search

hustvl / VAD

[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving
https://arxiv.org/abs/2303.12077
Apache License 2.0
493 stars 44 forks source link

Carla pre-trained weights #26

Open Wolfybox opened 9 months ago

Wolfybox commented 9 months ago

is there a release plan for Carla pre-trained weights?

rb93dett commented 8 months ago

VAD under CARLA environment is still developing. Currently, it is not prepared to be released, but we will make it open source as soon as possible.

jiaxiaosong1002 commented 3 weeks ago

@Wolfybox Hi, we are the authors of Bench2Drive and we would like to introduce that we have implemented VAD (non-official) in CARLA with code, checkpoints, and closed-loop results open sourced. Feel free to try it. https://github.com/Thinklab-SJTU/Bench2DriveZoo/tree/uniad/vad

turboxin commented 1 week ago

@Wolfybox Hi, we are the authors of Bench2Drive and we would like to introduce that we have implemented VAD (non-official) in CARLA with code, checkpoints, and closed-loop results open sourced. Feel free to try it. https://github.com/Thinklab-SJTU/Bench2DriveZoo/tree/uniad/vad

hi @jiaxiaosong1002， thanks for opensourcing this great work! I'm wondering how's the VAD closed-loop performence on CARLA of your implementation compared with official VAD results.

Looking forward to your reply! Thanks!

Wolfybox commented 1 week ago

@Wolfybox Hi, we are the authors of Bench2Drive and we would like to introduce that we have implemented VAD (non-official) in CARLA with code, checkpoints, and closed-loop results open sourced. Feel free to try it. https://github.com/Thinklab-SJTU/Bench2DriveZoo/tree/uniad/vad

Thanks for the good work. Starred.

jiaxiaosong1002 commented 1 week ago

@Wolfybox Hi, we are the authors of Bench2Drive and we would like to introduce that we have implemented VAD (non-official) in CARLA with code, checkpoints, and closed-loop results open sourced. Feel free to try it. https://github.com/Thinklab-SJTU/Bench2DriveZoo/tree/uniad/vad

hi @jiaxiaosong1002， thanks for opensourcing this great work! I'm wondering how's the VAD closed-loop performence on CARLA of your implementation compared with official VAD results.

Looking forward to your reply! Thanks!

Hi, since the benchmark and training set is very different, it is hard to conduct direct comparison.