Si Wu, Hau-San Wong, Wen Xue, Lianxin Xie, Le Jiang, Bingbing Zheng, Yunfei Zhang, Ruotao Xu
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.
Blind face video restoration aims to restore high-fidelity details from videos subjected to complex and unknown degradations. This task poses a significant challenge of managing temporal heterogeneity while at the same time maintaining stable face attributes. In this paper, we introduce a Discrete Prior-based Temporal-Coherent content prediction transformer to address the challenge, and our model is referred to as DP-TempCoh. Specifically, we incorporate a spatial-temporal-aware content prediction module to synthesize high-quality content from discrete visual priors, conditioned on degraded video tokens. To further enhance the temporal coherence of the predicted content, a motion statistics modulation module is designed to adjust the content, based on discrete motion priors in terms of cross-frame mean and variance. As a result, the statistics of the predicted content can match with that of real videos over time. By performing extensive experiments, we verify the effectiveness of the design elements and demonstrate the superior performance of our DP-TempCoh in both synthetically and naturally degraded video restoration.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.09960")
get_code_for_paper("2501.09960")
have("2501.09960")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2501.09960.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2501.09960)
Connect an agent — have() is free.