FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a large number of parameters and require heavy computation costs, largely hindering its application on low power-consumption devices such as mobile phones. In this paper, we tackle this challenge and design a lightweight model for fast and accurate optical flow prediction. Our proposed FastFlowNet follows the widely-used coarse-to-fine paradigm with following innovations. First, a new head enhanced pooling pyramid (HEPP) feature extractor is employed to intensify high-resolution pyramid features while reducing parameters. Second, we introduce a new center dense dilated correlation (CDDC) layer for constructing compact cost volume that can keep large search radius with reduced computation burden. Third, an efficient shuffle block decoder (SBD) is implanted into each pyramid level to accelerate flow estimation with marginal drops in accuracy. Experiments on both synthetic Sintel data and real-world KITTI datasets demonstrate the effectiveness of the proposed approach, which needs only 1/10 computation of comparable networks to achieve on par accuracy. In particular, FastFlowNet only contains 1.37M parameters; and can execute at 90 FPS (with a single GTX 1080Ti) or 5.7 FPS (embedded Jetson TX2 GPU) on a pair of Sintel images of resolution 1024x436.
Code (2)
Tasks
DecoderGPUOptical Flow EstimationSimilar Papers 제목 키워드 기반
Optical Flow Based Motion Detection for Autonomous Driving
Motion detection is a fundamental but challenging task for autonomous driving. In particular scenes like highway, remote objects have to be paid extra attention for better controlling decision. Aiming at distant vehicles…
Autonomous DrivingMotion DetectionOptical Flow EstimationFDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network
Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming trainin…
Optical Flow EstimationCross domain knowledge compression in realtime optical flow prediction on ultrasound sequences
In this paper, we propose an approach for realtime optical flow estimation in ultrasound sequences of vein and arteries based on knowledge distillation. Knowledge distillation is a technique to train a faster, smaller mo…
Knowledge DistillationOptical Flow EstimationA Lightweight Optical Flow CNN -- Revisiting Data Fidelity and Regularization
Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutiona…
Optical Flow EstimationHMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects
In optical flow estimation task, coarse-to-fine (C2F) warping strategy is widely used to deal with the large displacement problem and provides efficiency and speed. However, limited by the small search range between the …
Optical Flow Estimation