no code implementations • 11 Mar 2024 • Mingyue Zhao, Han Li, Li Fan, Shiyuan Liu, Xiaolan Qiu, S. Kevin Zhou
Then, we construct a geometry-aware dual-path propagation framework (GDP) to further promote complementary propagation learning, composed of hard geometry-aware propagation learning and soft geometry-aware propagation guidance.
1 code implementation • 6 Sep 2023 • Li Fan, Jeova Farias Sales Rocha Neto
We show that this approach leads to an estimator that is quicker, yields less estimation error and is less prone to failures than the traditional estimation procedures for this problem, even when we use a simple network.
no code implementations • 16 Mar 2023 • Mingyue Zhao, Shang Zhao, Quan Quan, Li Fan, Xiaolan Qiu, Shiyuan Liu, S. Kevin Zhou
To address these problems, we contribute a new bronchial segmentation method based on Group Deep Dense Supervision (GDDS) that emphasizes fine-scale bronchioles segmentation in a simple-but-effective manner.
no code implementations • 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) 2023 • Guo Haoran, Li Fan, Kuang Ping, Xiong Gang
Traffic sign recognition is committed to ensuring the safety of automatic driving.
Ranked #1 on Traffic Sign Detection on CCTSDB2021
3 code implementations • 1 Mar 2021 • Mu Hu, Shuling Wang, Bin Li, Shiyu Ning, Li Fan, Xiaojin Gong
More specifically, one branch inputs a color image and a sparse depth map to predict a dense depth map.
Ranked #3 on Depth Completion on KITTI Depth Completion