# DenseNet for Dense Flow

arXiv: https://arxiv.org/abs/1707.06316 · HTML: https://mlsanity.com/paper/1707.06316/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2017.

## Built on by (most cited first, 15 of 15)

- [A Comprehensive Review of Knowledge Distillation in Computer Vision](https://mlsanity.com/paper/2404.00936/) (2024)
- [Large-scale Detection of Marine Debris in Coastal Areas with Sentinel-2](https://mlsanity.com/paper/2307.02465/) (2023)
- [Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks](https://mlsanity.com/paper/2111.08591/) (2021)
- [Review of Face Presentation Attack Detection Competitions](https://mlsanity.com/paper/2112.11290/) (2021)
- [Dynamic Multi-scale Convolution for Dialect Identification](https://mlsanity.com/paper/2108.07787/) (2021)
- [MiddleGAN: Generate Domain Agnostic Samples for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2211.03144/) (2022)
- [Improving Medical Waste Classification with Hybrid Capsule Networks](https://mlsanity.com/paper/2503.10426/) (2025)
- [DOOMGAN:High-Fidelity Dynamic Identity Obfuscation Ocular Generative Morphing](https://mlsanity.com/paper/2507.17158/) (2025)
- [MMAP: A Multi-Magnification and Prototype-Aware Architecture for Predicting Spatial Gene Expression](https://mlsanity.com/paper/2510.11344/) (2025)
- [Detecting Network-based Internet Censorship via Latent Feature Representation Learning](https://mlsanity.com/paper/2209.05152/) (2022)
- [Evaluating the Reliability of CNN Models on Classifying Traffic and Road Signs using LIME](https://mlsanity.com/paper/2309.05747/) (2023)
- [Based on What We Can Control Artificial Neural Networks](https://mlsanity.com/paper/2310.05692/) (2023)
- [Face processing emerges from object-trained convolutional neural networks](https://mlsanity.com/paper/2405.18800/) (2024)
- [Deep learning and classical computer vision techniques in medical image analysis: Case studies on brain MRI tissue segmentation, lung CT COPD registration, and skin lesion classification](https://mlsanity.com/paper/2502.19258/) (2025)
- [A Residual Multi-task Network for Joint Classification and Regression in Medical Imaging](https://mlsanity.com/paper/2502.19692/) (2025)

## Abstract (arXiv)

Classical approaches for estimating optical flow have achieved rapid progress in the last decade. However, most of them are too slow to be applied in real-time video analysis. Due to the great success of deep learning, recent work has focused on using CNNs to solve such dense prediction problems. In this paper, we investigate a new deep architecture, Densely Connected Convolutional Networks (DenseNet), to learn optical flow. This specific architecture is ideal for the problem at hand as it provides shortcut connections throughout the network, which leads to implicit deep supervision. We extend current DenseNet to a fully convolutional network to learn motion estimation in an unsupervised manner. Evaluation results on three standard benchmarks demonstrate that DenseNet is a better fit than other widely adopted CNN architectures for optical flow estimation.