NTIRE 2023 challenge on efficient super-resolution: Methods and results

Y Li, Y Zhang, R Timofte, L Van Gool… - Proceedings of the …, 2023 - openaccess.thecvf.com
This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution
with a focus on the proposed solutions and results. The aim of this challenge is to devise a …

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

CY Wang, A Bochkovskiy… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Real-time object detection is one of the most important research topics in computer vision.
As new approaches regarding architecture optimization and training optimization are …

3d ux-net: A large kernel volumetric convnet modernizing hierarchical transformer for medical image segmentation

HH Lee, S Bao, Y Huo, BA Landman - arxiv preprint arxiv:2209.15076, 2022 - arxiv.org
The recent 3D medical ViTs (eg, SwinUNETR) achieve the state-of-the-art performances on
several 3D volumetric data benchmarks, including 3D medical image segmentation …

Make repvgg greater again: A quantization-aware approach

X Chu, L Li, B Zhang - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
The tradeoff between performance and inference speed is critical for practical applications.
Architecture reparameterization obtains better tradeoffs and it is becoming an increasingly …

Efficient deep models for real-time 4k image super-resolution. NTIRE 2023 benchmark and report

MV Conde, E Zamfir, R Timofte… - Proceedings of the …, 2023 - openaccess.thecvf.com
This paper introduces a novel benchmark for efficient upscaling as part of the NTIRE 2023
Real-Time Image Super-Resolution (RTSR) Challenge, which aimed to upscale images …

You only look once-object detection models: a review

A Nazir, MA Wani - 2023 10th International Conference on …, 2023 - ieeexplore.ieee.org
Object detection is the task of detecting instances of particular classes in an image. The You
Only Look Once (YOLO) object detection algorithms have become popular in recent years …

Mi-gan: A simple baseline for image inpainting on mobile devices

A Sargsyan, S Navasardyan, X Xu… - Proceedings of the …, 2023 - openaccess.thecvf.com
In recent years, many deep learning based image inpainting methods have been developed
by the research community. Some of those methods have shown impressive image …

YOLO-FA: Type-1 fuzzy attention based YOLO detector for vehicle detection

L Kang, Z Lu, L Meng, Z Gao - Expert Systems with Applications, 2024 - Elsevier
Vehicle detection is an important component of intelligent transportation systems and
autonomous driving. However, in real-world vehicle detection scenarios, the presence of …

Lighting every darkness in two pairs: A calibration-free pipeline for raw denoising

X **, JW **ao, LH Han, C Guo… - Proceedings of the …, 2023 - openaccess.thecvf.com
Calibration-based methods have dominated RAW image denoising under extremely low-
light environments. However, these methods suffer from several main deficiencies: 1) the …

YOLOPX: Anchor-free multi-task learning network for panoptic driving perception

J Zhan, Y Luo, C Guo, Y Wu, J Meng, J Liu - Pattern Recognition, 2024 - Elsevier
Panoptic driving perception encompasses traffic object detection, drivable area
segmentation, and lane detection. Existing methods typically utilize anchor-based multi-task …