MAP-Net
MAP-Net copied to clipboard
[CVPR'23] Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
from mmcv import Config, DictAction from mmcv.parallel import MMDataParallel from mmcv.runner import get_dist_info, init_dist, load_checkpoint from mmedit.apis import multi_gpu_test, set_random_seed, single_gpu_test from mmedit.core.distributed_wrapper import DistributedDataParallelWrapper from mmedit.datasets import build_dataloader, build_dataset...
Thanks for your work! How to dehazing on own video?
pretrained model: ConNeXt-tiny have problem
请问能否提供处理好的cityscapes部分的视频去雾数据集下载?
Hello, I am new to the openMMLabs framework, I tried to run inference on a video by adding a `demo_pipeline` in the `_base_/datasets/hazeworld.py` which I have seen from other openMMLabs...
请问您的雾天数据集是如何制作的?
Firstly I want to thank you for your work. Do you have colab support? And for training on a complete different dataset what process should I follow?