SkipSR: Faster Super Resolution with Token Skipping
Diffusion-based super-resolution (SR) is a key component in video generation and video restoration, but is slow and expensive, limiting scalability to higher resolutions and longer videos. Our key insight is that many regions in video are inherently low-detail and gain little from refinement, yet current methods process all pixels uniformly. To take advantage of this, we propose SkipSR, a simple framework for accelerating video SR by identifying low-detail regions directly from low-resolution input, then skipping computation on them entirely, only super-resolving the areas that require refinement. This simple yet effective strategy preserves perceptual quality in both standard and one-step diffusion SR models while significantly reducing computation. In standard SR benchmarks, our method achieves up to 60% faster end-to-end latency than prior models on 720p videos with no perceptible loss in quality. Video demos are available at https://rccchoudhury.github.io/skipsr/
Code (0)
등록된 구현이 없습니다.
Tasks
Video RestorationVideo GenerationSimilar Papers 제목 키워드 기반
SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens across historical scales at each autoregre…
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering …
Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference
Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in r…
Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models
This paper studies a hybrid language model (HLM) architecture that integrates a small language model (SLM) operating on a mobile device with a large language model (LLM) hosted at the base station (BS) of a wireless netw…
Language ModelingLanguage ModellingLarge Language ModelSmall Language ModelAdaptive Layer-skipping in Pre-trained LLMs
Various layer-skipping methods have been proposed to accelerate token generation in large language models (LLMs). However, they have overlooked a fundamental question: How do computational demands vary across the generat…
Text Generation