paper-with-me

Papers

DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement

2020-09-18 · Satoshi Iizuka, Edgar Simo-Serra

The remastering of vintage film comprises of a diversity of sub-tasks including super-resolution, noise removal, and contrast enhancement which aim to restore the deteriorated film medium to its original state. Additionally, due to the technical limitations of the time, most vintage film is either recorded in black and white, or has low quality colors, for which colorization becomes necessary. In this work, we propose a single framework to tackle the entire remastering task semi-interactively. Our work is based on temporal convolutional neural networks with attention mechanisms trained on videos with data-driven deterioration simulation. Our proposed source-reference attention allows the model to handle an arbitrary number of reference color images to colorize long videos without the need for segmentation while maintaining temporal consistency. Quantitative analysis shows that our framework outperforms existing approaches, and that, in contrast to existing approaches, the performance of our framework increases with longer videos and more reference color images.

📄 PDF Abstract BibTeX arXiv:2009.08692

Code (0)

등록된 구현이 없습니다.

Tasks

ColorizationDiversitySuper-ResolutionVideo Enhancement

Methods 이 논문이 사용한 방법론

Colorization Colorization is a self-supervision approach that relies on colorization as the pretext task in order to learn image representations.

Similar Papers 제목 키워드 기반

Spatiotemporal-Enhanced Network for Click-Through Rate Prediction in Location-based Services

2022-09-20 · Shaochuan Lin, Yicong Yu, Xiyu Ji, Taotao Zhou 외

In Location-Based Services(LBS), user behavior naturally has a strong dependence on the spatiotemporal information, i.e., in different geographical locations and at different times, user click behavior will change signif…

AttributeClick-Through Rate Prediction

Fragment and Integrate Network (FIN): A Novel Spatial-Temporal Modeling Based on Long Sequential Behavior for Online Food Ordering Click-Through Rate Prediction

2023-08-30 · Jun Li, Jingjian Wang, Hongwei Wang, Xing Deng 외

Spatial-temporal information has been proven to be of great significance for click-through rate prediction tasks in online Location-Based Services (LBS), especially in mainstream food ordering platforms such as DoorDash,…

Click-Through Rate PredictionRecommendation Systems

Convolutions Need Registers Too: HVS-Inspired Dynamic Attention for Video Quality Assessment

2026-01-16 · Mayesha Maliha R. Mithila, Mylene C. Q. Farias arxiv

No-reference video quality assessment (NR-VQA) estimates perceptual quality without a reference video, which is often challenging. While recent techniques leverage saliency or transformer attention, they merely address g…

Video Quality AssessmentSaliency Prediction

TimeColor: Flexible Reference Colorization via Temporal Concatenation

2026-01-01 · Bryan Constantine Sadihin, Yihao Meng, Michael Hua Wang, Matteo Jiahao Chen 외 arxiv

Most colorization models condition only on a single reference, typically the first frame of the scene. However, this approach ignores other sources of conditional data, such as character sheets, background images, or arb…

Temporal User Profiling with LLMs: Balancing Short-Term and Long-Term Preferences for Recommendations

2025-08-11 · Milad Sabouri, Masoud Mansoury, Kun Lin, Bamshad Mobasher arxiv

Accurately modeling user preferences is crucial for improving the performance of content-based recommender systems. Existing approaches often rely on simplistic user profiling methods, such as averaging or concatenating …