Shichen Peng

Mr. Shichen Peng

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
12 January 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
SPShichen Peng
Shichen Peng
JLJiaming Liu
Jiaming Liu
ZLZihao Liu
Zihao Liu
HZHongzhong Zheng
Hongzhong Zheng
DNDimin Niu
Dimin Niu
Yibo FanYibo Fan
Yibo Fan
Blind Face Restoration (BFR) involves restoring high-quality images from various unknown and severely degraded counterparts, which is a challenging task due to the conflicting objectives of content reconstruction and detail generation. In this paper, we propose a closely-coupled approach to address this problem and achieve photorealistic and faithful reproductions. Specifically, we propose a two-step image restoration model that consists of the following steps: Firstly, we train a BaseNet that incorporates a filtered feature fusion module ($F^{3}M$) to purify degraded feature maps. Secondly, while keeping the BaseNet fixed, we train a DetailNet that utilizes a feature probabilistic model to generate high-frequency detail information. The proposed framework not only separates the reconstruction and generation processes but also deeply analyzes their interactions, leading to an optimized balance between perceptual quality and fidelity. Our approach is validated through extensive experiments on both synthetic datasets and real-world facial photographs, demonstrating significant improvements in Frechet Inception Distance (FID) scores while maintaining identity consistency. The experimental results highlight our method's state-of-the-art performance, achieving superior visual quality and processing efficiency compared to existing methods.

1 January 2026 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
SPShichen Peng
Shichen Peng
YGYupeng Gui
Yupeng Gui
RTRuiqi Tang
Ruiqi Tang
ZCZhengyang Cao
Zhengyang Cao
QLQiuyu Li
Qiuyu Li
Yibo FanYibo Fan
Yibo Fan

22 June 2026
Verified
Conference Paper
Open access
SPShichen Peng
Shichen Peng
QLQiuyu Li
Qiuyu Li
YGYupeng Gui
Yupeng Gui
HHHan He
Han He
ZCZhengyang Cao
Zhengyang Cao
Yibo FanYibo Fan
Yibo Fan

11 November 2026 in Integration
Verified
Journal Article
Closed access
SPShichen Peng
Shichen Peng
ZZZiqing Zhang
Ziqing Zhang
YGYupeng Gui
Yupeng Gui
RTRuiqi Tang
Ruiqi Tang
QLQiuyu Li
Qiuyu Li
Yibo FanYibo Fan
Yibo Fan

14 October 2026 in Simulation Modelling Practice and Theory
Verified
Journal Article
Closed access
SPShichen Peng
Shichen Peng
ZZZiqing Zhang
Ziqing Zhang
RTRuiqi Tang
Ruiqi Tang
YGYupeng Gui
Yupeng Gui
QLQiuyu Li
Qiuyu Li
Yibo FanYibo Fan
Yibo Fan

18 August 2025 in Electronics
Verified
Journal Article
Open access
PDF file
HZHao Zhang
Hao Zhang
JHJianheng He
Jianheng He
YGYupeng Gui
Yupeng Gui
SPShichen Peng
Shichen Peng
LHLeilei Huang
Leilei Huang
Yibo FanYibo Fan
Yibo Fan
Convolutional neural networks (CNNs) have achieved remarkable success in computer vision tasks, driving the rapid development of hardware accelerators. However, memory efficiency remains a key challenge, as conventional accelerators adopt layer-by-layer processing, leading to frequent external memory accesses (EMAs) of intermediate feature data, which increase energy consumption and latency. While layer fusion has been proposed to enhance inter-layer feature reuse, existing approaches typically rely on fixed data management tailored to specific architectures, introducing on-chip memory overhead and requiring trade-offs with EMAs. Moreover, prevalent residual connections further weaken fusion benefits due to diverse data reuse distances. To address these challenges, we propose layer-centric tile fusion, which integrates residual data loading with feature merging by leveraging receptive field relationships among feature tiles. A reuse distance-aware caching strategy is introduced to support flexible storage for various data types. We also develop a modeling framework to analyze the trade-off between on-chip memory usage and EMA-induced energy-delay product (EDP). Experimental results demonstrate that our method achieves 5.04–43.44% EDP reduction and 20.28–58.33% memory usage reduction compared to state-of-the-art designs on ResNet-18 and SRGAN.