Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution
Conventional super-resolution (SR) schemes make heavy use of convolutional neural networks (CNNs), which involve intensive multiply-accumulate (MAC) operations, and require specialized hardware such as graphics processing units. This contradicts the regime of edge AI that often runs on devices strained by power, computing, and storage resources. Such a challenge has motivated a series of lookup table (LUT)-based SR schemes that employ simple LUT readout and largely elude CNN computation. Nonetheless, the multi-megabyte LUTs in existing methods still prohibit on-chip storage and necessitate off-chip memory transport. This work tackles this storage hurdle and innovates hundred-kilobyte LUT (HKLUT) models amenable to on-chip cache. Utilizing an asymmetric two-branch multistage network coupled with a suite of specialized kernel patterns, HKLUT demonstrates an uncompromising performance and superior hardware efficiency over existing LUT schemes. Our implementation is publicly available at: https://github.com/jasonli0707/hklut.
Code (1)
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution
Lookup table (LUT) has shown its efficacy in low-level vision tasks due to the valuable characteristics of low computational cost and hardware independence. However, recent attempts to address the problem of single image…
Image Super-ResolutionSuper-ResolutionEfficient Neural Network Encoding for 3D Color Lookup Tables
3D color lookup tables (LUTs) enable precise color manipulation by mapping input RGB values to specific output RGB values. 3D LUTs are instrumental in various applications, including video editing, in-camera processing, …
Color ManipulationEfficient Neural NetworkVideo EditingLearnable Lookup Table for Neural Network Quantization
Neural network quantization aims at reducing bit-widths of weights and activations for memory and computational efficiency. Since a linear quantizer (i.e., round(*) function) cannot well fit the bell-shaped distribut…
Computational Efficiencyimage-classificationImage ClassificationImage Super-Resolution+3A New Hyperelastic Lookup Table for RT-DC
Real-time deformability cytometry (RT-DC) is an established method that quantifies features like size, shape, and stiffness for whole cell populations on a single-cell level in real time. To extract the cell stiffness, a…
Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables
Deep models are capable of fitting complex high dimensional functions while usually yielding large computation load. There is no way to speed up the inference process by classical lookup tables due to the high-dimensiona…
CPU