paper-with-me

홈 › Papers

Stochastic Video Prediction with Structure and Motion

2022-03-20 · Adil Kaan Akan, Sadra Safadoust, Fatma Güney

While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot provide reliable predictions for scenes with a moving camera and independently moving foreground objects in driving scenarios. The existing methods fail to fully capture the dynamics of the structured world by only focusing on changes in pixels. In this paper, we assume that there is an underlying process creating observations in a video and propose to factorize it into static and dynamic components. We model the static part based on the scene structure and the ego-motion of the vehicle, and the dynamic part based on the remaining motion of the dynamic objects. By learning separate distributions of changes in foreground and background, we can decompose the scene into static and dynamic parts and separately model the change in each. Our experiments demonstrate that disentangling structure and motion helps stochastic video prediction, leading to better future predictions in complex driving scenarios on two real-world driving datasets, KITTI and Cityscapes.

📄 PDF Abstract BibTeX arXiv:2203.10528

Code (0)

등록된 구현이 없습니다.

Tasks

Future predictionPredictionVideo Prediction

Similar Papers 제목 키워드 기반

State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend

2024-04-17 · Fei Cui, Jiaojiao Fang, Xiaojiang Wu, Zelong Lai 외

Stochastic video prediction enables the consideration of uncertainty in future motion, thereby providing a better reflection of the dynamic nature of the environment. Stochastic video prediction methods based on image au…

motion predictionPredictionState Space ModelsVideo Prediction

SLAMP: Stochastic Latent Appearance and Motion Prediction

2021-08-05 · ICCV 2021 10 · Adil Kaan Akan, Erkut Erdem, Aykut Erdem, Fatma Güney

Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components. Most of the previous work utilizing motion is deterministic but there are stochastic meth…

Autonomous Drivingmotion predictionPredictionVideo Generation+1

STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Prediction

2023-12-11 · Xi Ye, Guillaume-Alexandre Bilodeau

Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents. In this paper, we propose a novel video prediction model, which ha…

PredictionVideo Prediction

Inference-time Stochastic Refinement of GRU-Normalizing Flow for Real-time Video Motion Transfer

2025-12-03 · Tasmiah Haque, Srinjoy Das arxiv

Real-time video motion transfer applications such as immersive gaming and vision-based anomaly detection require accurate yet diverse future predictions to support realistic synthesis and robust downstream decision makin…

Time Series ForecastingAnomaly DetectionDecision Making

Unsupervised Learning of Object Structure and Dynamics from Videos

2019-06-19 · NeurIPS 2019 12 · Matthias Minderer, Chen Sun, Ruben Villegas, Forrester Cole 외

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stoc…

Action Recognitioncontinuous-controlContinuous ControlObject+2