paper-with-me

홈 › Papers

Bicubic++: Slim, Slimmer, Slimmest -- Designing an Industry-Grade Super-Resolution Network

2023-05-03 · Bahri Batuhan Bilecen, Mustafa Ayazoglu

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.

📄 PDF Abstract BibTeX arXiv:2305.02126

Code (1)

aselsan-research-imaging-team/bicubic-plusplus 공식 구현 pytorch

Tasks

4kImage Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

SlimmeRF: Slimmable Radiance Fields

2023-12-15 · Shiran Yuan, Hao Zhao

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 Synthesis

KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging

2026-03-01 · Lianjun Liu, Hongli An, Weiqi Yan, Xin Du 외 arxiv

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

2025-10-10 · Ian Harshbarger, Calvin Chidambaram arxiv

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 Learning

EffNet: An Efficient Structure for Convolutional Neural Networks

2018-01-19 · Ido Freeman, Lutz Roese-Koerner, Anton Kummert

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

2025-11-14 · Wei-Cheng Lee, Francesco Orabona arxiv

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 …