LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

07/18/2020
by   Tak-Wai Hui, et al.
9

Deep learning approaches have achieved great success in addressing the problem of optical flow estimation. The keys to success lie in the use of cost volume and coarse-to-fine flow inference. However, the matching problem becomes ill-posed when partially occluded or homogeneous regions exist in images. This causes a cost volume to contain outliers and affects the flow decoding from it. Besides, the coarse-to-fine flow inference demands an accurate flow initialization. Ambiguous correspondence yields erroneous flow fields and affects the flow inferences in subsequent levels. In this paper, we introduce LiteFlowNet3, a deep network consisting of two specialized modules, to address the above challenges. (1) We ameliorate the issue of outliers in the cost volume by amending each cost vector through an adaptive modulation prior to the flow decoding. (2) We further improve the flow accuracy by exploring local flow consistency. To this end, each inaccurate optical flow is replaced with an accurate one from a nearby position through a novel warping of the flow field. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.

READ FULL TEXT

page 12

page 13

research
01/31/2021

OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow

Optical flow estimation is an essential step for many real-world compute...
research
11/04/2020

CoT-AMFlow: Adaptive Modulation Network with Co-Teaching Strategy for Unsupervised Optical Flow Estimation

The interpretation of ego motion and scene change is a fundamental task ...
research
04/17/2023

LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation

Lack of texture often causes ambiguity in matching, and handling this is...
research
06/09/2023

DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow

Recent advancements in neural network-based optical flow estimation ofte...
research
02/20/2018

Devon: Deformable Volume Network for Learning Optical Flow

We propose a lightweight neural network model, Deformable Volume Network...
research
03/31/2021

DCVNet: Dilated Cost Volume Networks for Fast Optical Flow

The cost volume, capturing the similarity of possible correspondences ac...
research
03/08/2021

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation

Dense optical flow estimation plays a key role in many robotic vision ta...

Please sign up or login with your details

Forgot password? Click here to reset