paper-with-me

홈 › Papers

DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos

2023-04-13 · CVPR 2023 1 · Qi Zhao, M. Salman Asif, Zhan Ma

Existing implicit neural representation (INR) methods do not fully exploit spatiotemporal redundancies in videos. Index-based INRs ignore the content-specific spatial features and hybrid INRs ignore the contextual dependency on adjacent frames, leading to poor modeling capability for scenes with large motion or dynamics. We analyze this limitation from the perspective of function fitting and reveal the importance of frame difference. To use explicit motion information, we propose Difference Neural Representation for Videos (DNeRV), which consists of two streams for content and frame difference. We also introduce a collaborative content unit for effective feature fusion. We test DNeRV for video compression, inpainting, and interpolation. DNeRV achieves competitive results against the state-of-the-art neural compression approaches and outperforms existing implicit methods on downstream inpainting and interpolation for $960 \times 1920$ videos.

📄 PDF Abstract BibTeX arXiv:2304.06544

Code (0)

등록된 구현이 없습니다.

Tasks

Video Compression

Methods 이 논문이 사용한 방법론

Test 설명 없음
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

Latent Trajectory Discrimination for AI-Generated Text Detection

2026-07-16 · Gianluca Bonifazi, Christopher Buratti, Michele Marchetti, Federica Parlapiano 외 arxiv

Most existing approaches to AI-Generated Text Detection (AIGTD) treat documents as static objects and base their decisions on aggregate statistics or globally compressed embeddings. However, this perspective overlooks th…

Contrastive LearningText Detection

Towards Measuring and Modeling Geometric Structures in Time Series Forecasting via Image Modality

2025-07-31 · Mingyang Yu, Xiahui Guo, Peng chen, Zhenkai Li 외 arxiv

Time Series forecasting is critical in diverse domains such as weather forecasting, financial investment, and traffic management. While traditional numerical metrics like mean squared error (MSE) can quantify point-wise …

Time Series ForecastingWeather Forecasting

DyG$^2$T: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer

2026-08-19 · Yansong Wang, Zhaobo Qi, Xinyan Liu, Beichen Zhang 외 arxiv

Modeling object dynamics from limited visual observations is a fundamental problem for enabling accurate motion trajectory prediction in embodied interaction scenarios. Existing dynamics modeling methods first compress r…

Trajectory Prediction

Wavelet Predictive Representations for Non-Stationary Reinforcement Learning

2025-10-06 · Min Wang, Xin Li, Ye He, Yao-Hui Li 외 arxiv

The real world is inherently non-stationary, with ever-changing factors, such as weather conditions and traffic flows, making it challenging for agents to adapt to varying environmental dynamics. Non-Stationary Reinforce…

Time Series ForecastingReinforcement Learning

Learning Hierarchical Dynamics with Spatial Adjacency for Image Enhancement

2022-08-10 · ACMMM 2022 8 · Yudong Liang, Bin Wang, Wenqi Ren, Jiaying Liu 외

In various real-world image enhancement applications, the degradations are always non-uniform or non-homogeneous and diverse, which challenges most deep networks with fixed parameters during the inference phase. Inspired…

Image DehazingImage EnhancementLow-Light Image EnhancementRain Removal