Lin Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Lin Zhu has a total of 133 co-authors. Here are the top co-authors by number of shared publications:
- Yonghong Tian
School of Computer Science, Peking University, Beijing, China
31 shared publications - Xiao Wang
Anhui University
27 shared publications - Bo Jiang
School of Computer Science and Technology, Anhui University, Hefei, China
16 shared publications - Hua Huang
School of Artificial Intelligence, Beijing Normal University, Beijing, China, Beijing Key Laboratory of Artificial Intelligence for Education, Beijing, China, and Engineering Research Center of Intelligent Technology and Educational Application, Ministry of Education, Beijing, China
16 shared publications - Lizhi Wang
School of Artificial Intelligence, Beijing Normal University, Beijing, China
13 shared publications - Yaowei Wang
Harbin Institute of Technology (Shenzhen), Shenzhen, China and Pengcheng Laboratory, Shenzhen, China
10 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5154-5163
DTRNet: Dual Text-Radical Decoding for Handwritten Chinese Text Recognition with Faked Character Detection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5154-5163
Open AccessDTRNet: Dual Text-Radical Decoding for Handwritten Chinese Text Recognition with Faked Character Detection
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 15382-15399
E 3 NeRF: Efficient Event-Enhanced Neural Radiance Fields From Blurry Images
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 15382-15399
E 3 NeRF: Efficient Event-Enhanced Neural Radiance Fields From Blurry Images
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 15180-15197
Bridging the Gap in Exam Handwritten Text Recognition: Dataset, Benchmark, and Modeling
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (11) , 15180-15197
Bridging the Gap in Exam Handwritten Text Recognition: Dataset, Benchmark, and Modeling
- 11 September 2026
- Published by Springer Nature
- p. 334-352
Event Stream-Based Sign Language Translation: A High-Definition Benchmark Dataset and A Novel Baseline
- 11 September 2026
- Published by Springer Nature
- p. 334-352
Event Stream-Based Sign Language Translation: A High-Definition Benchmark Dataset and A Novel Baseline
- 1 August 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (8) , 377
Human Activity Recognition using RGB-DVS Cameras: A Multi-modal Heat Conduction Model and A Benchmark Dataset
- 1 August 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (8) , 377
Human Activity Recognition using RGB-DVS Cameras: A Multi-modal Heat Conduction Model and A Benchmark Dataset
- 22 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Event Temporal Upsampling through High Frame Rate Brightness Changes Estimation
Event cameras offer unique advantages such as high temporal resolution and low power consumption. However, under slow-motion or low-light scenarios, the resulting event streams are often sparse, limiting the performance of event-based vision algorithms. In this paper, we propose a novel temporal upsampling framework that enhances the temporal resolution of sparse events by estimating high-frame-rate brightness changes. Our method first reconstructs long-term brightness changes from sparse input events using a neural network, then optimizes short-term high-frame-rate brightness variations through a spatiotemporal smoothness and sparsity-constrained model. Following the generation principle of event cameras, new events are synthesized when estimated brightness changes exceed the firing threshold. To evaluate the effectiveness of our method, we construct a temporal upsampling dataset and introduce two event-based metrics to directly assess the quality of upsampled events. Extensive experiments demonstrate that our approach can generate denser and more informative events, significantly enhancing the performance of downstream tasks, including image reconstruction, optical flow estimation, and object detection in sparse conditions.
- 22 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Event Temporal Upsampling through High Frame Rate Brightness Changes Estimation
Event cameras offer unique advantages such as high temporal resolution and low power consumption. However, under slow-motion or low-light scenarios, the resulting event streams are often sparse, limiting the performance of event-based vision algorithms. In this paper, we propose a novel temporal upsampling framework that enhances the temporal resolution of sparse events by estimating high-frame-rate brightness changes. Our method first reconstructs long-term brightness changes from sparse input events using a neural network, then optimizes short-term high-frame-rate brightness variations through a spatiotemporal smoothness and sparsity-constrained model. Following the generation principle of event cameras, new events are synthesized when estimated brightness changes exceed the firing threshold. To evaluate the effectiveness of our method, we construct a temporal upsampling dataset and introduce two event-based metrics to directly assess the quality of upsampled events. Extensive experiments demonstrate that our approach can generate denser and more informative events, significantly enhancing the performance of downstream tasks, including image reconstruction, optical flow estimation, and object detection in sparse conditions.
- Top Cited Papers
- 9 March 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (4) , 181
Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
- 9 March 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (4) , 181
Top Cited PapersEvent Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (6) , 6470-6487
DSNeRF: Dynamic View Synthesis for Ultra-Fast Scenes From Continuous Spike Streams
Spike cameras generate binary spikes in response to light intensity changes, enabling high-speed visual perception with unprecedented temporal resolution. However, the unique characteristics of spike stream present significant challenges for reconstructing dense 3D scene representations, particularly in dynamic environments and under non-ideal lighting conditions. In this paper, we introduce DSNeRF, the first method to derive a NeRF-based volumetric scene representation from spike camera data. Our approach leverages NeRF’s multi-view consistency to establish robust self-supervision, effectively eliminating erroneous measurements and uncovering coherent structures within exceedingly noisy input amidst diverse real-world illumination scenarios. We propose a novel mapping from pixel rays to the spike domain, integrating the spike generation process directly into NeRF training. Specifically, DSNeRF introduces an integrate-and-fire neuron layer that models non-idealities to capture intrinsic camera noise, including both random and fixed-pattern spike noise, thereby enhancing scene fidelity. Additionally, we propose a motion-guided spiking neuron layer and a long-term rendering photometric loss to better align dynamic spike streams, ensuring accurate scene geometry. Our method optimizes neural radiance fields to render photorealistic novel views from continuous spike streams, demonstrating advantages over other vision sensors in certain scenes. Empirical evaluations on both real and simulated sequences validate the effectiveness of our approach.
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (6) , 6470-6487
DSNeRF: Dynamic View Synthesis for Ultra-Fast Scenes From Continuous Spike Streams
Spike cameras generate binary spikes in response to light intensity changes, enabling high-speed visual perception with unprecedented temporal resolution. However, the unique characteristics of spike stream present significant challenges for reconstructing dense 3D scene representations, particularly in dynamic environments and under non-ideal lighting conditions. In this paper, we introduce DSNeRF, the first method to derive a NeRF-based volumetric scene representation from spike camera data. Our approach leverages NeRF’s multi-view consistency to establish robust self-supervision, effectively eliminating erroneous measurements and uncovering coherent structures within exceedingly noisy input amidst diverse real-world illumination scenarios. We propose a novel mapping from pixel rays to the spike domain, integrating the spike generation process directly into NeRF training. Specifically, DSNeRF introduces an integrate-and-fire neuron layer that models non-idealities to capture intrinsic camera noise, including both random and fixed-pattern spike noise, thereby enhancing scene fidelity. Additionally, we propose a motion-guided spiking neuron layer and a long-term rendering photometric loss to better align dynamic spike streams, ensuring accurate scene geometry. Our method optimizes neural radiance fields to render photorealistic novel views from continuous spike streams, demonstrating advantages over other vision sensors in certain scenes. Empirical evaluations on both real and simulated sequences validate the effectiveness of our approach.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (4) , 3952-3969
Learning Physics-Informed Noise Models from Dark Frames for Low-Light Raw Image Denoising
Recently, the mainstream practice for training low-light raw image denoising methods has shifted towards employing synthetic data. Noise modeling, which focuses on characterizing the noise distribution of real-world sensors, profoundly influences the effectiveness and practicality of synthetic data. Currently, physics-based noise modeling struggles to characterize the entire real noise distribution, while learning-based noise modeling impractically depends on paired real data. In this paper, we propose a novel strategy: learning the noise model from dark frames instead of paired real data, to break down the data dependency. Based on this strategy, we introduce an efficient physics-informed noise neural proxy (PNNP) to approximate the real-world sensor noise model. Specifically, we integrate physical priors into neural proxies and introduce three efficient techniques: physics-guided noise decoupling (PND), physics-aware proxy model (PPM), and differentiable distribution loss (DDL). PND decouples the dark frame into different components and handles different levels of noise flexibly, which reduces the complexity of noise modeling. PPM incorporates physical priors to constrain the synthetic noise, which promotes the accuracy of noise modeling. DDL provides explicit and reliable supervision for noise distribution, which promotes the precision of noise modeling. PNNP exhibits powerful potential in characterizing the real noise distribution. Extensive experiments on public datasets demonstrate superior performance in practical low-light raw image denoising. The source code will be publicly available at the https://fenghansen.github.io/publication/PNNP.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (4) , 3952-3969
Learning Physics-Informed Noise Models from Dark Frames for Low-Light Raw Image Denoising
Recently, the mainstream practice for training low-light raw image denoising methods has shifted towards employing synthetic data. Noise modeling, which focuses on characterizing the noise distribution of real-world sensors, profoundly influences the effectiveness and practicality of synthetic data. Currently, physics-based noise modeling struggles to characterize the entire real noise distribution, while learning-based noise modeling impractically depends on paired real data. In this paper, we propose a novel strategy: learning the noise model from dark frames instead of paired real data, to break down the data dependency. Based on this strategy, we introduce an efficient physics-informed noise neural proxy (PNNP) to approximate the real-world sensor noise model. Specifically, we integrate physical priors into neural proxies and introduce three efficient techniques: physics-guided noise decoupling (PND), physics-aware proxy model (PPM), and differentiable distribution loss (DDL). PND decouples the dark frame into different components and handles different levels of noise flexibly, which reduces the complexity of noise modeling. PPM incorporates physical priors to constrain the synthetic noise, which promotes the accuracy of noise modeling. DDL provides explicit and reliable supervision for noise distribution, which promotes the precision of noise modeling. PNNP exhibits powerful potential in characterizing the real noise distribution. Extensive experiments on public datasets demonstrate superior performance in practical low-light raw image denoising. The source code will be publicly available at the https://fenghansen.github.io/publication/PNNP.
- Open Access
Decoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking
Existing RGB-Event visual object tracking approaches primarily rely on conventional feature-level fusion, failing to fully exploit the unique advantages of event cameras. In particular, the high dynamic range and motion-sensitive nature of event cameras are often overlooked, while low-information regions are processed uniformly, leading to unnecessary computational overhead for the backbone network. To address these issues, we propose a novel tracking framework that performs early fusion in the frequency domain, enabling effective aggregation of high-frequency information from the event modality. Specifically, RGB and event modalities are transformed from the spatial domain to the frequency domain via the Fast Fourier Transform, with their amplitude and phase components decoupled. High-frequency event information is selectively fused into RGB modality through amplitude and phase attention, enhancing feature representation while substantially reducing backbone computation. In addition, a motion-guided spatial sparsification module leverages the motion-sensitive nature of event cameras to capture the relationship between target motion cues and spatial probability distribution, filtering out low-information regions and enhancing target-relevant features. Finally, a sparse set of target-relevant features is fed into the backbone network for learning, and the tracking head predicts the final target position. Extensive experiments on three widely used RGB-Event tracking benchmark datasets, including FE108, FELT, and COESOT, demonstrate the high performance and efficiency of our method. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvTracking
Open AccessDecoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking
Existing RGB-Event visual object tracking approaches primarily rely on conventional feature-level fusion, failing to fully exploit the unique advantages of event cameras. In particular, the high dynamic range and motion-sensitive nature of event cameras are often overlooked, while low-information regions are processed uniformly, leading to unnecessary computational overhead for the backbone network. To address these issues, we propose a novel tracking framework that performs early fusion in the frequency domain, enabling effective aggregation of high-frequency information from the event modality. Specifically, RGB and event modalities are transformed from the spatial domain to the frequency domain via the Fast Fourier Transform, with their amplitude and phase components decoupled. High-frequency event information is selectively fused into RGB modality through amplitude and phase attention, enhancing feature representation while substantially reducing backbone computation. In addition, a motion-guided spatial sparsification module leverages the motion-sensitive nature of event cameras to capture the relationship between target motion cues and spatial probability distribution, filtering out low-information regions and enhancing target-relevant features. Finally, a sparse set of target-relevant features is fed into the backbone network for learning, and the tracking head predicts the final target position. Extensive experiments on three widely used RGB-Event tracking benchmark datasets, including FE108, FELT, and COESOT, demonstrate the high performance and efficiency of our method. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvTracking