paper-with-me

홈 › Papers

Kalman-Inspired Feature Propagation for Video Face Super-Resolution

2024-08-09 · Ruicheng Feng, Chongyi Li, Chen Change Loy

Despite the promising progress of face image super-resolution, video face super-resolution remains relatively under-explored. Existing approaches either adapt general video super-resolution networks to face datasets or apply established face image super-resolution models independently on individual video frames. These paradigms encounter challenges either in reconstructing facial details or maintaining temporal consistency. To address these issues, we introduce a novel framework called Kalman-inspired Feature Propagation (KEEP), designed to maintain a stable face prior over time. The Kalman filtering principles offer our method a recurrent ability to use the information from previously restored frames to guide and regulate the restoration process of the current frame. Extensive experiments demonstrate the effectiveness of our method in capturing facial details consistently across video frames. Code and video demo are available at https://jnjaby.github.io/projects/KEEP.

📄 PDF Abstract BibTeX arXiv:2408.05205

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-ResolutionSuper-ResolutionVideo Super-Resolution

Similar Papers 제목 키워드 기반

Interpretable Deep Feature Propagation for Early Action Recognition

2021-07-11 · He Zhao, Richard P. Wildes

Early action recognition (action prediction) from limited preliminary observations plays a critical role for streaming vision systems that demand real-time inference, as video actions often possess elongated temporal spa…

Action RecognitionPrediction

Match4Annotate: Propagating Sparse Video Annotations via Implicit Neural Feature Matching

2026-03-06 · Zhuorui Zhang, Roger Pallarès-López, Praneeth Namburi, Brian W. Anthony arxiv

Acquiring per-frame video annotations remains a primary bottleneck for deploying computer vision in specialized domains such as medical imaging, where expert labeling is slow and costly. Label propagation offers a natura…

One-Shot Segmentation

K-Track: Kalman-Enhanced Tracking for Accelerating Deep Point Trackers on Edge Devices

2025-12-11 · Bishoy Galoaa, Pau Closas, Sarah Ostadabbas arxiv

Point tracking in video sequences is a foundational capability for real-world computer vision applications, including robotics, autonomous systems, augmented reality, and video analysis. While recent deep learning-based …

Point Tracking

Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering

2018-09-17 · Jessica S. Titensky, Hayden Jananthan, Jeremy Kepner

Extended Kalman Filtering (EKF) can be used to propagate and quantify input uncertainty through a Deep Neural Network (DNN) assuming mild hypotheses on the input distribution. This methodology yields results comparable t…

Deep Kalman Filtering Network for Video Compression Artifact Reduction

2018-09-01 · ECCV 2018 9 · Guo Lu, Wanli Ouyang, Dong Xu, Xiaoyun Zhang 외

When lossy video compression algorithms are applied, compression artifacts often appear in videos, making decoded videos unpleasant for human visual systems. In this paper, we model the video artifact reduction task as a…

Video Compression