DDCNet-Multires: Effective Receptive Field Guided Multiresolution CNN for Dense Prediction

TL;DR

This paper introduces DDCNet-Multires, a compact multiresolution CNN guided by effective receptive field strategies, improving dense optical flow estimation in scenes with large displacements and heterogeneous motion.

Contribution

It extends previous DDCNet designs by cascading sub-nets with decreasing ERF extents to handle complex motion dynamics without adding specialized layers.

Findings

Outperforms previous DDCNet variants in accuracy.

Achieves comparable results to lightweight methods on benchmark datasets.

Remains compact and efficient for dense optical flow tasks.

Abstract

Dense optical flow estimation is challenging when there are large displacements in a scene with heterogeneous motion dynamics, occlusion, and scene homogeneity. Traditional approaches to handle these challenges include hierarchical and multiresolution processing methods. Learning-based optical flow methods typically use a multiresolution approach with image warping when a broad range of flow velocities and heterogeneous motion is present. Accuracy of such coarse-to-fine methods is affected by the ghosting artifacts when images are warped across multiple resolutions and by the vanishing problem in smaller scene extents with higher motion contrast. Previously, we devised strategies for building compact dense prediction networks guided by the effective receptive field (ERF) characteristics of the network (DDCNet). The DDCNet design was intentionally simple and compact allowing it to be used as a building block for designing more complex yet compact networks. In this work, we extend the DDCNet strategies to handle heterogeneous motion dynamics by cascading DDCNet based sub-nets with decreasing extents of their ERF. Our DDCNet with multiresolution capability (DDCNet-Multires) is compact without any specialized network layers. We evaluate the performance of the DDCNet-Multires network using standard optical flow benchmark datasets. Our experiments demonstrate that DDCNet-Multires improves over the DDCNet-B0 and -B1 and provides optical flow estimates with accuracy comparable to similar lightweight learning-based methods.