Junyong Lee, Sunghyun Cho, Seungyong Lee, Myeonghee Lee
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose the first reference-based video superresolution (RefVSR) approach that utilizes reference videos for high-fidelity results. We focus on RefVSR in a triplecamera setting, where we aim at super-resolving a lowresolution ultra-wide video utilizing wide-angle and telephoto videos. We introduce the first RefVSR network that recurrently aligns and propagates temporal reference features fused with features extracted from low-resolution frames. To facilitate the fusion and propagation of temporal reference features, we propose a propagative temporal fusion module. For learning and evaluation of our network, we present the first RefVSR dataset consisting of triplets of ultra-wide, wide-angle, and telephoto videos concurrently taken from triple cameras of a smartphone. We also propose a twostage training strategy fully utilizing video triplets in the proposed dataset for real-world 4× video super-resolution. We extensively evaluate our method, and the result shows the state-of-the-art performance in 4× super-resolution.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.14537")
get_code_for_paper("2203.14537")
have("2203.14537")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.14537.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.14537)
Connect an agent — have() is free.