Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer

arXiv:2404.13640v1 Announce Type: cross
Abstract: Multiple complex degradations are coupled in low-quality video faces in the real world. Therefore, blind video face restoration is a highly challenging ill-posed problem, requiring not only hallucinating high-fidelity details but also enhancing temporal coherence across diverse pose variations. Restoring each frame independently in a naive manner inevitably introduces temporal incoherence and artifacts from pose changes and keypoint localization errors. To address this, we propose the first blind video face restoration approach with a novel …

alignment arxiv beyond blind cs.cv cs.mm eess.iv face parsing restoration temporal transformer type via video