FG-DFPN: Flow Guided Deformable Frame Prediction Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yılmaz, M. Akın, Bilican, Ahmet, Tekalp, A. Murat
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915198243176448
author Yılmaz, M. Akın
Bilican, Ahmet
Tekalp, A. Murat
author_facet Yılmaz, M. Akın
Bilican, Ahmet
Tekalp, A. Murat
contents Video frame prediction remains a fundamental challenge in computer vision with direct implications for autonomous systems, video compression, and media synthesis. We present FG-DFPN, a novel architecture that harnesses the synergy between optical flow estimation and deformable convolutions to model complex spatio-temporal dynamics. By guiding deformable sampling with motion cues, our approach addresses the limitations of fixed-kernel networks when handling diverse motion patterns. The multi-scale design enables FG-DFPN to simultaneously capture global scene transformations and local object movements with remarkable precision. Our experiments demonstrate that FG-DFPN achieves state-of-the-art performance on eight diverse MPEG test sequences, outperforming existing methods by 1dB PSNR while maintaining competitive inference speeds. The integration of motion cues with adaptive geometric transformations makes FG-DFPN a promising solution for next-generation video processing systems that require high-fidelity temporal predictions. The model and instructions to reproduce our results will be released at: https://github.com/KUIS-AI-Tekalp-Research Group/frame-prediction
format Preprint
id arxiv_https___arxiv_org_abs_2503_11343
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FG-DFPN: Flow Guided Deformable Frame Prediction Network
Yılmaz, M. Akın
Bilican, Ahmet
Tekalp, A. Murat
Image and Video Processing
Computer Vision and Pattern Recognition
Video frame prediction remains a fundamental challenge in computer vision with direct implications for autonomous systems, video compression, and media synthesis. We present FG-DFPN, a novel architecture that harnesses the synergy between optical flow estimation and deformable convolutions to model complex spatio-temporal dynamics. By guiding deformable sampling with motion cues, our approach addresses the limitations of fixed-kernel networks when handling diverse motion patterns. The multi-scale design enables FG-DFPN to simultaneously capture global scene transformations and local object movements with remarkable precision. Our experiments demonstrate that FG-DFPN achieves state-of-the-art performance on eight diverse MPEG test sequences, outperforming existing methods by 1dB PSNR while maintaining competitive inference speeds. The integration of motion cues with adaptive geometric transformations makes FG-DFPN a promising solution for next-generation video processing systems that require high-fidelity temporal predictions. The model and instructions to reproduce our results will be released at: https://github.com/KUIS-AI-Tekalp-Research Group/frame-prediction
title FG-DFPN: Flow Guided Deformable Frame Prediction Network
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.11343