A5115603825- Advanced Optical Sensing Technologies
- Advanced Vision and Imaging
- Neuroendocrine regulation and behavior
- Advanced Image Processing Techniques
- Advanced Memory and Neural Computing
- Hypothalamic control of reproductive hormones
- Advanced MRI Techniques and Applications
- Traumatic Brain Injury and Neurovascular Disturbances
- Image and Signal Denoising Methods
- Liver Disease Diagnosis and Treatment
- Neural Networks and Reservoir Computing
- Reproductive Biology and Fertility
- Animal Behavior and Reproduction
- Spinal Cord Injury Research
- Reproductive Physiology in Livestock
- Intracerebral and Subarachnoid Hemorrhage Research
- Fetal and Pediatric Neurological Disorders
- Alcohol Consumption and Health Effects
- Human Pose and Action Recognition
- Sparse and Compressive Sensing Techniques
- Cardiac, Anesthesia and Surgical Outcomes
- Medical Imaging Techniques and Applications
- Advanced Neural Network Applications
- Autophagy in Disease and Therapy
- CCD and CMOS Imaging Sensors
Sichuan University
2023-2024
West China Hospital of Sichuan University
2023-2024
Jinan University
2024
West China Medical Center of Sichuan University
2023
Huawei Technologies (France)
2021-2022
Northwest A&F University
2022
Sun Yat-sen University
2000
State-of-the-art frame interpolation methods generate intermediate frames by inferring object motions in the image from consecutive key-frames. In absence of additional information, first-order approximations, i.e. optical flow, must be used, but this choice restricts types that can modeled, leading to errors highly dynamic scenarios. Event cameras are novel sensors address limitation providing auxiliary visual information blind-time between frames. They asynchronously measure per-pixel...
Recently, video frame interpolation using a combination of frame- and event-based cameras has surpassed traditional image-based methods both in terms performance memory efficiency. However, current still suffer from (i) brittle image-level fusion complementary results, that fails the presence artifacts fused image, (ii) potentially temporally inconsistent inefficient motion estimation procedures, run for every inserted (iii) low contrast regions do not trigger events, thus cause events-only...
Modern high dynamic range (HDR) imaging pipelines align and fuse multiple low (LDR) images captured at different exposure times. While these methods work well in static scenes, scenes remain a challenge since the LDR still suffer from saturation noise. In such scenarios, event cameras would be valid complement, thanks to their higher temporal resolution range. this paper, we propose first multi-bracket HDR pipeline combining standard camera with an camera. Our results show better overall...
Non-alcoholic fatty liver disease (NAFLD) is a common metabolic disorder worldwide, with an increasing incidence in recent years. While previous studies have suggested association between the air pollutant PM2.5 and NAFLD, there still considerable debate regarding existence of clear causal relationship pollution NAFLD. This study aims to employ Mendelian randomization methods evaluate major pollutants
State-of-the-art frame interpolation methods generate intermediate frames by inferring object motions in the image from consecutive key-frames. In absence of additional information, first-order approximations, i.e. optical flow, must be used, but this choice restricts types that can modeled, leading to errors highly dynamic scenarios. Event cameras are novel sensors address limitation providing auxiliary visual information blind-time between frames. They asynchronously measure per-pixel...
Rapid and reliable identification of dynamic scene parts, also known as motion segmentation, is a key challenge for mobile sensors. Contemporary RGB camera-based methods rely on modeling camera properties however, are often under-constrained fall short in unknown categories. Event cameras have the potential to overcome these limitations, but corresponding only been demonstrated smaller-scale indoor environments with simplified objects. This work presents an event-based method class-agnostic...
Modern high dynamic range (HDR) imaging pipelines align and fuse multiple low (LDR) images captured at different exposure times. While these methods work well in static scenes, scenes remain a challenge since the LDR still suffer from saturation noise. In such scenarios, event cameras would be valid complement, thanks to their higher temporal resolution range. this paper, we propose first multi-bracket HDR pipeline combining standard camera with an camera. Our results show better overall...
Recently, video frame interpolation using a combination of frame- and event-based cameras has surpassed traditional image-based methods both in terms performance memory efficiency. However, current still suffer from (i) brittle image-level fusion complementary results, that fails the presence artifacts fused image, (ii) potentially temporally inconsistent inefficient motion estimation procedures, run for every inserted (iii) low contrast regions do not trigger events, thus cause events-only...