Research map / Video / Video segmentation and tracking
QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution
Zhenwei Zhang, Fanhua Shang, Hongying Liu, Liang Wan, Wei Feng, Yanming Hui
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes QBasicVSR, a quantization method for video super-resolution networks that addresses temporal error propagation, shared temporal parameterization, and temporal metric mismatch to enable mobile deployment.
Problem
Quantizing video super-resolution networks for mobile deployment degrades performance because of temporal error propagation, shared temporal parameterization, and temporal metric mismatch; prior quantization work targets only image super-resolution.
Approach
A temporal-awareness adaptation quantization scheme designed specifically for video SR, rather than transferring image SR quantization methods directly. The abstract only states the motivation; the specific mechanism is not given in the provided text.
Experimental setup
Builds on: BasicVSR
Closest papers by meaning
- QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution (AAAI 2026 · similarity 0.92)
- TAQ: Static-Deployable Temporal-Aware Quantization for Real-World Video Super-Resolution (ECCV 2026 · similarity 0.90)
- 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution (NeurIPS 2024 · similarity 0.87)
- PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement (NeurIPS 2025 · similarity 0.87)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.86)
- AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
