Bicubic++: Slim, Slimmer, Slimmest -- Designing an Industry-Grade Super-Resolution Network
We propose a real-time and lightweight single-image super-resolution (SR) network named Bicubic++. Despite using spatial dimensions of the input image across the whole network, Bicubic++ first learns quick reversible downgraded and lower resolution features of the image in order to decrease the number of computations. We also construct a training pipeline, where we apply an end-to-end global structured pruning of convolutional layers without using metrics like magnitude and gradient norms, and focus on optimizing the pruned network's PSNR on the validation set. Furthermore, we have experimentally shown that the bias terms take considerable amount of the runtime while increasing PSNR marginally, hence we have also applied bias removal to the convolutional layers. Our method adds ~1dB on Bicubic upscaling PSNR for all tested SR datasets and runs with ~1.17ms on RTX3090 and ~2.9ms on RTX3070, for 720p inputs and 4K outputs, both in FP16 precision. Bicubic++ won NTIRE 2023 RTSR Track 2 x3 SR competition and is the fastest among all competitive methods. Being almost as fast as the standard Bicubic upsampling method, we believe that Bicubic++ can set a new industry standard.
Code (1)
Tasks
4kImage Super-ResolutionSuper-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SlimmeRF: Slimmable Radiance Fields
Neural Radiance Field (NeRF) and its variants have recently emerged as successful methods for novel view synthesis and 3D scene reconstruction. However, most current NeRF models either achieve high accuracy using large m…
3D Scene ReconstructionNeRFNovel View SynthesisKVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging
The growing computational and memory demands of the Key-Value (KV) cache significantly limit the ability of Large Language Models (LLMs). While KV merging has emerged as a promising solution, existing methods that rely o…
Slim Scheduler: A Runtime-Aware RL and Scheduler System for Efficient CNN Inference
Most neural network scheduling research focuses on optimizing static, end-to-end models of fixed width, overlooking dynamic approaches that adapt to heterogeneous hardware and fluctuating runtime conditions. We present S…
Reinforcement LearningEffNet: An Efficient Structure for Convolutional Neural Networks
With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware. Slimmer models have therefore become a hot research …
A Best-of-Both-Worlds Proof for Tsallis-INF without Fenchel Conjugates
In this short note, we present a simple derivation of the best-of-both-world guarantee for the Tsallis-INF multi-armed bandit algorithm from J. Zimmert and Y. Seldin. Tsallis-INF: An optimal algorithm for stochastic and …