D
Dongwei Ren
Researcher at Tianjin University
Publications - 59
Citations - 3879
Dongwei Ren is an academic researcher from Tianjin University. The author has contributed to research in topics: Computer science & Deblurring. The author has an hindex of 18, co-authored 47 publications receiving 1317 citations. Previous affiliations of Dongwei Ren include Harbin Institute of Technology & Hong Kong Polytechnic University.
Papers
More filters
Journal ArticleDOI
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
TL;DR: A Distance-IoU (DIoU) loss is proposed by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training than IoU and GIoU losses, thereby leading to faster convergence and better performance.
Proceedings ArticleDOI
Progressive Image Deraining Networks: A Better and Simpler Baseline
TL;DR: Wren et al. as discussed by the authors proposed a simple baseline deraining network by considering network architecture, input and output, and loss functions, which can be used as a suitable baseline in future deraining research.
Posted Content
Progressive Image Deraining Networks: A Better and Simpler Baseline
TL;DR: A better and simpler baseline deraining network by considering network architecture, input and output, and loss functions is provided and is expected to serve as a suitable baseline in future deraining research.
Posted Content
Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
TL;DR: This paper proposes Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression, leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency.
Proceedings ArticleDOI
Neural Blind Deconvolution Using Deep Priors
TL;DR: Experimental results show that the proposed SelfDeblur can achieve notable quantitative gains as well as more visually plausible deblurring results in comparison to state-of-the-art blind deconvolution methods on benchmark datasets and real-world blurry images.