Peiqi Duan

Peiqi Duan

Auto-generated profile, based on publicly available information

Peiqi Duan

State Key Laboratory for Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 February 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JHJin Han
Jin Han
YYYixin Yang
Yixin Yang
PDPeiqi Duan
Peiqi Duan
CZChu Zhou
Chu Zhou
LMLei Ma
Lei Ma
BSBoxin Shi
Boxin Shi
Reconstruction of high dynamic range image from a single low dynamic range image captured by a conventional RGB camera, which suffers from over- or under-exposure, is an ill-posed problem. In contrast, recent neuromorphic cameras like event camera and spike camera can record high dynamic range scenes in the form of intensity maps, but with much lower spatial resolution and no color information. In this paper, we propose a hybrid imaging system (denoted as NeurImg) that captures and fuses the visual information from a neuromorphic camera and ordinary images from an RGB camera to reconstruct high-quality high dynamic range images and videos. The proposed NeurImg-HDR+ network consists of specially designed modules, which bridges the domain gaps on resolution, dynamic range, and color representation between two types of sensors and images to reconstruct high-resolution, high dynamic range images and videos. We capture a test dataset of hybrid signals on various HDR scenes using the hybrid camera, and analyze the advantages of the proposed fusing strategy by comparing it to state-of-the-art inverse tone mapping methods and merging two low dynamic range images approaches. Quantitative and qualitative experiments on both synthetic data and real-world scenarios demonstrate the effectiveness of the proposed hybrid high dynamic range imaging system. Code and dataset can be found at: https://github.com/hjynwa/NeurImg-HDR

1 October 2023
Verified
Conference Paper
Closed access
JLJinxiu Liang
Jinxiu Liang
YYYixin Yang
Yixin Yang
BLBoyu Li
Boyu Li
PDPeiqi Duan
Peiqi Duan
YXYong Xu
Yong Xu
BSBoxin Shi
Boxin Shi
With frame-based cameras, capturing fast-moving scenes without suffering from blur often comes at the cost of low SNR and low contrast. Worse still, the photometric constancy that enhancement techniques heavily relied on is fragile for frames with short exposure. Event cameras can record brightness changes at an extremely high temporal resolution. For low-light videos, event data are not only suitable to help capture temporal correspondences but also provide alternative observations in the form of intensity ratios between consecutive frames and exposure-invariant information. Motivated by this, we propose a low-light video enhancement method with hybrid inputs of events and frames. Specifically, a neural network is trained to establish spatiotemporal coherence between visual signals with different modalities and resolutions by constructing correlation volume across space and time. Experimental results on synthetic and real data demonstrate the superiority of the proposed method compared to the state-of-the-art methods.

20 September 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
PDPeiqi Duan
Peiqi Duan
ZWZihao Wang
Zihao Wang
BSBoxin Shi
Boxin Shi
OCOliver Cossairt
Oliver Cossairt
THTiejun Huang
Tiejun Huang
AKAggelos Katsaggelos
Aggelos Katsaggelos
Many visual and robotics tasks in real-world scenarios rely on robust handling of high speed motion and high dynamic range (HDR) with effectively high spatial resolution and low noise. Such stringent requirements, however, cannot be directly satisfied by a single imager or modality, rather by complementary sensors. In this paper, we explore the synergy between traditional frame-based sensors with high spatial resolution and low sensor noise, and emerging event-based sensors with high speed and high dynamic range. We introduce a novel computational framework, termed Guided Event Filtering (GEF), to process the two streams of input data and output super-resolved yet noise-reduced events. GEF first associates the events with the reference image via a flow model. It then performs joint filtering that inherits the mutual structure from both inputs, with a switch mechanism for event self-guided filtering. Lastly, GEF re-distributes the filtered events in the space-time volume while preserving the statistical characteristics of the original events. We demonstrate the benefits of GEF by applying the output high quality events to existing event-based algorithms across diverse application categories, including high speed corner tracking, depth estimation, high frame-rate video synthesis, and super resolution/HDR/color image restoration.

14 August 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
PDPeiqi Duan
Peiqi Duan
YMYi Ma
Yi Ma
XZXinyu Zhou
Xinyu Zhou
XSXinyu Shi
Xinyu Shi
ZWZihao W. Wang
Zihao W. Wang
BSBoxin Shi
Boxin Shi
Neuromorphic cameras are emerging imaging technology that has advantages over conventional imaging sensors in several aspects including dynamic range, sensing latency, and power consumption. However, the signal-to-noise level and the spatial resolution still fall behind the state of conventional imaging sensors. In this paper, we address the denoising and super-resolution problem for modern neuromorphic cameras. We employ 3D U-Net as the backbone neural architecture for such a task. The networks are trained and tested on two types of neuromorphic cameras: a dynamic vision sensor and a spike camera. Their pixels generate signals asynchronously, the former is based on perceived light changes and the latter is based on accumulated light intensity. To collect the datasets for training such networks, we design a display-camera system to record high frame-rate videos at multiple resolutions, providing supervision for denoising and super-resolution. The networks are trained in a noise-to-noise fashion, where the two ends of the network are unfiltered noisy data. The output of the networks has been tested for downstream applications including event-based visual object tracking and image reconstruction. Experimental results demonstrate the effectiveness of improving the quality of neuromorphic events and spikes, and the corresponding improvement to downstream applications with state-of-the-art performance.

9 May 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
PDPeiqi Duan
Peiqi Duan
BLBoyu Li
Boyu Li
YYYixin Yang
Yixin Yang
HLHanyue Lou
Hanyue Lou
MTMinggui Teng
Minggui Teng
BSBoxin Shi
Boxin Shi
Event cameras are emerging imaging technology that offer advantages over conventional frame-based imaging sensors in dynamic range and sensing speed. Complementing the rich texture and color perception of traditional image frames, the hybrid camera system of event and frame-based cameras enables high-performance imaging. With the assistance of event cameras, high-quality image/video enhancement methods make it possible to break the limits of traditional frame-based cameras, especially exposure time, resolution, dynamic range, and frame rate limits. This paper focuses on five event-aided image and video enhancement tasks (i.e., event-based video reconstruction, event-aided high frame rate video reconstruction, image deblurring, image super-resolution, and high dynamic range image reconstruction), provides an analysis of the effects of different event properties, a real-captured and ground truth labeled benchmark dataset, a unified benchmarking of state-of-the-art methods, and an evaluation for two mainstream event simulators. In detail, this paper collects a real-captured evaluation dataset EventAid for five event-aided image/video enhancement tasks, by using “Event-RGB” multi-camera hybrid system, taking into account scene diversity and spatiotemporal synchronization. We further perform quantitative and visual comparisons for state-of-the-art algorithms, provide a controlled experiment to analyze the performance limit of event-aided image deblurring methods, and discuss open problems to inspire future research.

5 April 2022 in Asian Journal of Andrology
Verified
Journal Article
Open access
BSBin Sun
Bin Sun
HCHeng-Gui Chen
Heng-Gui Chen
PDPeng Duan
Peng Duan
ZTZhou-Zheng Tu
Zhou-Zheng Tu
YCYingjun Chen
Yingjun Chen
APAn Pan
An Pan
Accumulating epidemiological evidence shows that handgrip strength provides predictive potential in physical, mental, and reproductive health status. However, the associations between handgrip strength and semen characteristics have not been explored. We recruited 1382 eligible men at the Hubei Province Human Sperm Bank (Wuhan, China) who had their handgrip strength measured at recruitment and provided 6458 repeated semen specimens within a 6-month period. Semen characteristics, including semen volume, sperm motility parameters (immotility, nonprogressive motility, and progressive motility), and sperm concentration, were assessed. Mixed-effect models and restricted cubic spline functions were applied to investigate the relationship of handgrip strength with repeated measurements of semen characteristics. After adjusting for confounding factors, the mixed-effect models revealed that handgrip strength was positively associated with semen volume, sperm concentration, progressive motility, total motility, and total count (all P for trend < 0.05). Compared to men in the lowest quartile, those in the highest quartile of handgrip strength had higher semen volume, sperm concentration, progressive motility, total motility, and total count, with measurements of 14.2% (95% confidence interval [CI]: 5.9%–23.2%), 19.5% (95% CI: 7.3%–33.1%), 9.5% (95% CI: 3.4%–15.9%), 8.8% (95% CI: 3.2%–14.6%), and 36.4% (95% CI: 18.9%–56.5%), respectively. These positive dose-response relationships were further confirmed in restricted cubic splines, where handgrip strength was modeled as a continuous variable. Handgrip strength, as an indicator of muscular function and strength, was positively associated with semen characteristics in a dose-dependent manner.