Minggui Teng

Minggui Teng

Auto-generated profile, based on publicly available information

Minggui Teng

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

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
17 August 2022 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
HCHaoyu Chen
Haoyu Chen
MTMinggui Teng
Minggui Teng
BSBoxin Shi
Boxin Shi
YWYizhou Wang
Yizhou Wang
THTiejun Huang
Tiejun Huang
Event cameras are bio-inspired cameras that can measure the intensity change asynchronously with high temporal resolution. One of the advantages of event cameras is that they suffer less from motion blur than traditional frame cameras when recording daily scenes with fast-moving objects. In this paper, we formulate the deblurring task on traditional cameras directed by events to be a residual learning one, and propose corresponding network architectures for effective learning of deblurring and high frame rate video generation tasks. We first train a modified U-Net network to restore a sharp image from a blurry image using the corresponding events. Then we train another similar network by replacing the downsampling blocks with blocks of the convolutional long short-term memory (Conv-LSTM) to recurrently generate high frame rate video using the restored sharp image and part of the events. Benefitting from the blur-free events and the proposed learning strategy, the experimental results show that the proposed method outperforms state-of-the-art methods for generating sharp images and high frame rate videos.

6 March 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
CZChu Zhou
Chu Zhou
YHYufei Han
Yufei Han
MTMinggui Teng
Minggui Teng
JHJin Han
Jin Han
SLSi Li
Si Li
BSBoxin Shi
Boxin Shi
Taking photos with digital cameras often accompanies saturated pixels due to their limited dynamic range, and it is far too ill-posed to restore them. Capturing multiple low dynamic range images with bracketed exposures can make the problem less ill-posed, however, it is prone to ghosting artifacts caused by spatial misalignment among images. A polarization camera can capture four spatially-aligned and temporally-synchronized polarized images with different polarizer angles in a single shot, which can be used for ghost-free high dynamic range (HDR) reconstruction. However, real-world scenarios are still challenging since existing polarization-based HDR reconstruction methods treat all pixels in the same manner and only utilize the spatially-variant exposures of the polarized images (without fully exploiting the degree of polarization (DoP) and the angle of polarization (AoP) of the incoming light to the sensor, which encode abundant structural and contextual information of the scene) to handle the problem still in an ill-posed manner. In this paper, we propose a pixel-wise depolarization strategy to solve the polarization guided HDR reconstruction problem, by classifying the pixels based on their levels of ill-posedness in HDR reconstruction procedure and applying different solutions to different classes. To utilize the strategy with better generalization ability and higher robustness, we propose a network-physics-hybrid polarization-based HDR reconstruction pipeline along with a neural network tailored to it, fully exploiting the DoP and AoP. Experimental results show that our approach achieves state-of-the-art performance on both synthetic and real-world images.

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.

25 July 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
MTMinggui Teng
Minggui Teng
HLHanyue Lou
Hanyue Lou
YYYixin Yang
Yixin Yang
THTiejun Huang
Tiejun Huang
BSBoxin Shi
Boxin Shi
Creating an image focal stack requires multiple shots, which captures images at different depths within the same scene. Such methods are not suitable for scenes undergoing continuous changes. Achieving an all-in-focus image from a single shot poses significant challenges, due to the highly ill-posed nature of rectifying defocus and deblurring from a single image. In this paper, to restore an all-in-focus image, we introduce the neuromorphic focal stack, which is defined as neuromorphic signal streams captured by an event/ a spike camera during a continuous focal sweep, aiming to restore an all-in-focus image. Given an RGB image focused at any distance, we harness the high temporal resolution of neuromorphic signal streams. From neuromorphic signal streams, we automatically select refocusing timestamps and reconstruct corresponding refocused images to form a focal stack. Guided by the neuromorphic signal around the selected timestamps, we can merge the focal stack using proper weights and restore a sharp all-in-focus image. We test our method on two distinct neuromorphic cameras. Experimental results from both synthetic and real datasets demonstrate a marked improvement over existing State-of-the-Art methods.

28 May 2026 in IEEE Transactions on Computational Imaging
Verified
Journal Article
Closed access
YLYixing Liu
Yixing Liu
MTMinggui Teng
Minggui Teng
YXYifei Xia
Yifei Xia
PDPeiqi Duan
Peiqi Duan
BSBoxin Shi
Boxin Shi
Atmospheric turbulence degrades image quality by introducing spatially varying blur and geometric tilt distortions, posing significant challenges to downstream computer vision tasks including segmentation and recognition. Existing single-image and multi-frame methods struggle with the highly ill-posed nature of this problem due to the compositional complexity of turbulence-induced distortions. To address this, we propose EvTurb, an event guided turbulence removal framework that leverages high-speed event streams to decouple blur and tilt effects. EvTurb uses event-derived cues in a novel two-step event-guided network: event integrals are first employed as empirical guidance to reduce blur in the coarse outputs. This is followed by employing a variance map, derived from raw event streams, to eliminate the tilt distortion for the refined outputs. Additionally, we present TurbEvent, the first real-captured dataset featuring diverse turbulence scenarios. Experimental results demonstrate that EvTurb surpasses state-of-the-art methods while maintaining computational efficiency.

12 February 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
MTMinggui Teng
Minggui Teng
SXSuhang Xuan
Suhang Xuan
ZYZhiang Yan
Zhiang Yan
HLHanyue Lou
Hanyue Lou
BLBoyu Li
Boyu Li
BSBoxin Shi
Boxin Shi
Traditional cameras face limitations in maintaining focus across dynamic scenes, especially during rapid motion, due to the constraints of their lenses. Post-capture refocusing techniques, including deep learning-based methods and light field cameras, have been explored to mitigate these challenges. However, these approaches frequently struggle with temporal consistency or experience a trade-off in spatial resolution. In this paper, we introduce the coded event focal stack, a novel approach that captures both motion and depth information through event streams recorded during a modulated focal sweep. Our coded event focal stack enables the generation of full-time intermediate frames refocused at arbitrary focal distances. Extensive experiments on both synthetic and real-world datasets demonstrate the superior refocusing capability of our method over state-of-the-art techniques, particularly in dynamic scenes with complex motion and depth variations.