Kai-Ping Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kai-Ping Lin has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Chao-Tsung Huang
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan
3 shared publications An-Yu Cheng
National Tsing Hua University, Hsinchu, Taiwan
1 shared publicationChun-Yeh Lin
Department of Electrical Engineering, National Tsing-Hua University, Hsinchu, Taiwan
1 shared publicationHao-Chien Cheng
National Tsing Hua University, Hsinchu, Taiwan
1 shared publicationHong-Chuan Liao
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan
1 shared publication- Jia-Han Liu
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan
1 shared publication
Latest Publications
- 12 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 60 (9) , 3416-3427
VISTA: A Memory-Efficient CNN Processor for Video and Image Spatial/Temporal Interpolation Acceleration
Video convolutional neural networks (V-CNNs) take multiple frames as input and leverage temporal information to enhance quality and temporal consistency, making them promising solutions for high-resolution imaging tasks, such as video super-resolution (VSR) and video frame interpolation (VFI). Previous works have proposed CNN accelerators for single-image high-resolution imaging tasks, using layer-fusion (LF) workflows to reduce the need for external memory access (EMA) of intermediate feature maps (FMs). However, V-CNNs demand more EMA and computational complexity, posing implementation challenges for edge devices. Additionally, using deformable convolution (DC) to break through the fixed shape of the kernel receptive field can improve image quality and temporal consistency but requires additional storage and computational logic. In this article, we present a memory-efficient V-CNN processor, VISTA. We introduce a cuboid-based LF (CBLF) workflow for V-CNNs to reuse temporal information from overlapped FMs at different time points, reducing EMA and computational complexity. Moreover, the VISTA adopts a heterogeneous reuse-recomputing approach to handle overlaps between region-of-influence (ROI) pyramids and uses reference-frame-first scheduling (RFFS) to reduce the need for extensive memory usage during cross-frame alignment computations. Furthermore, we apply a hardware-model co-design to devise tile-based offset-confined DC (TODC), which reduces computational logic and saves line buffer usage for the search window with 0.06–0.18 dB of peak signal-to-noise ratio (PSNR) drop in image quality. The 12.6-mm2 VISTA is fabricated using 40-nm CMOS technology and achieves peak throughput of 4K-UHD 60 and 50 frames/s for supporting VSR and VFI applications, respectively. It reduces 33%–53% of input EMA, 19% of activation static random-access memory (SRAM), and 19%–42% of computational complexity.
- 12 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 60 (9) , 3416-3427
VISTA: A Memory-Efficient CNN Processor for Video and Image Spatial/Temporal Interpolation Acceleration
Video convolutional neural networks (V-CNNs) take multiple frames as input and leverage temporal information to enhance quality and temporal consistency, making them promising solutions for high-resolution imaging tasks, such as video super-resolution (VSR) and video frame interpolation (VFI). Previous works have proposed CNN accelerators for single-image high-resolution imaging tasks, using layer-fusion (LF) workflows to reduce the need for external memory access (EMA) of intermediate feature maps (FMs). However, V-CNNs demand more EMA and computational complexity, posing implementation challenges for edge devices. Additionally, using deformable convolution (DC) to break through the fixed shape of the kernel receptive field can improve image quality and temporal consistency but requires additional storage and computational logic. In this article, we present a memory-efficient V-CNN processor, VISTA. We introduce a cuboid-based LF (CBLF) workflow for V-CNNs to reuse temporal information from overlapped FMs at different time points, reducing EMA and computational complexity. Moreover, the VISTA adopts a heterogeneous reuse-recomputing approach to handle overlaps between region-of-influence (ROI) pyramids and uses reference-frame-first scheduling (RFFS) to reduce the need for extensive memory usage during cross-frame alignment computations. Furthermore, we apply a hardware-model co-design to devise tile-based offset-confined DC (TODC), which reduces computational logic and saves line buffer usage for the search window with 0.06–0.18 dB of peak signal-to-noise ratio (PSNR) drop in image quality. The 12.6-mm2 VISTA is fabricated using 40-nm CMOS technology and achieves peak throughput of 4K-UHD 60 and 50 frames/s for supporting VSR and VFI applications, respectively. It reduces 33%–53% of input EMA, 19% of activation static random-access memory (SRAM), and 19%–42% of computational complexity.
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 32 (11) , 2093-2106
VLSI Design of Light-Field Factorization for Dual-Layer Factored Display
This article introduces a VLSI design for light-field factorization, aimed at enhancing immersive 3-D visual experiences for computational light-field factored displays. The main design challenges are intensive memory-access demands and high computational complexity. Accordingly, we first propose half-block-based factorization (HBBF) and sparse ray sampling (SRS) to reduce DRAM bandwidth by 99% and SRAM size by 74%. Then, we devise integer hybrid quantization (INTH) to cut down computational logic by 41%, leading to improvements in die area and power efficiency. Finally, we fabricated a processor chip that incorporates 75.1 kB of SRAM and 5.9M logic gates using 40-nm CMOS technology. It can operate with three different performance modes: high quality (56.9 MPixel/s at 971 mW), balanced (62.5 MPixel/s at 442 mW), and low power (61.7 MPixel/s at 283 mW). Across these modes, its normalized energy ranges between 4.4 and 16.2 nJ/pixel. This implementation surpasses existing GPU platforms and offers an$85\times $ increase in processing speed and a$311\times $ reduction in power consumption. We also showcase a real-time computational 3-D display system with this chip, demonstrating its practical efficacy in computational 3-D display technology.- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 32 (11) , 2093-2106
VLSI Design of Light-Field Factorization for Dual-Layer Factored Display
This article introduces a VLSI design for light-field factorization, aimed at enhancing immersive 3-D visual experiences for computational light-field factored displays. The main design challenges are intensive memory-access demands and high computational complexity. Accordingly, we first propose half-block-based factorization (HBBF) and sparse ray sampling (SRS) to reduce DRAM bandwidth by 99% and SRAM size by 74%. Then, we devise integer hybrid quantization (INTH) to cut down computational logic by 41%, leading to improvements in die area and power efficiency. Finally, we fabricated a processor chip that incorporates 75.1 kB of SRAM and 5.9M logic gates using 40-nm CMOS technology. It can operate with three different performance modes: high quality (56.9 MPixel/s at 971 mW), balanced (62.5 MPixel/s at 442 mW), and low power (61.7 MPixel/s at 283 mW). Across these modes, its normalized energy ranges between 4.4 and 16.2 nJ/pixel. This implementation surpasses existing GPU platforms and offers an$85\times $ increase in processing speed and a$311\times $ reduction in power consumption. We also showcase a real-time computational 3-D display system with this chip, demonstrating its practical efficacy in computational 3-D display technology.- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Solid-State Circuits Letters
- Vol. 7, 26-29
CINE: A 4K-UHD Energy-Efficient Computational Imaging Neural Engine With Overlapped Stripe Inference and Structure-Sparse Kernel
Recently, convolutional neural networks have achieved great success in high-resolution computational imaging applications such as super-resolution, image denoising, and image style transfer. However, it demands an enormous number of external memory access, i.e. DRAM bandwidth, and intensive computation while inferencing deeper models for high-quality images. In this letter, an energy-efficient computational imaging neural engine, CINE, is proposed with three key features: 1) overlapped stripe inference flow; 2) structure-sparse convolution kernel; 3) weight-rotated allocation unit. As a result, CINE can provide 4.6-8.3 TOP/W of energy efficiency for high-quality computational imaging applications.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Solid-State Circuits Letters
- Vol. 7, 26-29
CINE: A 4K-UHD Energy-Efficient Computational Imaging Neural Engine With Overlapped Stripe Inference and Structure-Sparse Kernel
Recently, convolutional neural networks have achieved great success in high-resolution computational imaging applications such as super-resolution, image denoising, and image style transfer. However, it demands an enormous number of external memory access, i.e. DRAM bandwidth, and intensive computation while inferencing deeper models for high-quality images. In this letter, an energy-efficient computational imaging neural engine, CINE, is proposed with three key features: 1) overlapped stripe inference flow; 2) structure-sparse convolution kernel; 3) weight-rotated allocation unit. As a result, CINE can provide 4.6-8.3 TOP/W of energy efficiency for high-quality computational imaging applications.