CVOct 4, 2017

Secrets in Computing Optical Flow by Convolutional Networks

arXiv:1710.01462v1
Originality Synthesis-oriented
AI Analysis

This work addresses optical flow estimation for computer vision applications, but it appears incremental as it builds on existing CNN-based methods like FlowNet.

The paper tackled the problem of optical flow estimation by proposing several convolutional neural network architectures and fully unveiling the intrinsic differences between these structures, but no concrete results or numbers are provided.

Convolutional neural networks (CNNs) have been widely used over many areas in compute vision. Especially in classification. Recently, FlowNet and several works on opti- cal estimation using CNNs shows the potential ability of CNNs in doing per-pixel regression. We proposed several CNNs network architectures that can estimate optical flow, and fully unveiled the intrinsic different between these structures.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes