Efficient Video Enhancement Transformer

Florin-Alexandru Vasluianu, Radu TimofteICIP 2022 · OpenReview

Abstract

Video Enhancement is an important computer vision task aiming at the removal of the artifacts from a lossy compressed video and the improvement of the visual properties by a photo-realistic restoration of the video contents. Decades of research produced a multitude of efficient algorithms, enabling the reduction of the memory footprint of the transferred video contents in a contiguously increasing network of video streaming services. In this work, we propose VETRAN - a low latency real-time online Video Enhancement TRANsformer based on spatial and temporal attention mechanisms. We validate our method on recent Video Enhancement NTIRE and AIM challenge benchmarks, i.e. REDS/REDS4, LDV, and IntVID. We improve over the compared state-of-the-art methods both quantitatively and qualitatively, while maintaining a low inference time.
BibTeX
@inproceedings{vasluianu2022efficient,
  author = {Florin-Alexandru Vasluianu and Radu Timofte},
  title = {{Efficient Video Enhancement Transformer}},
  booktitle = {ICIP},
  year = {2022},
  url = {https://openreview.net/forum?id=9GreCiHR7D},
}

Loading related content...

Figure