DenseNet for dense flow

Zhu, Yi; Newsam, Shawn

doi:10.1109/icip.2017.8296389

Cited by 219 publications

(97 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to unsupervised optical flow learning, the advantage of our learned conditional prior becomes obvious. Although DenseNetF [40] and UnFlowC [27] employ more powerful network structures than FlowNetS, their EPEs on MPI-Sintel Test are still 1.5 higher than our CPNFlow. Note that in [27], several versions of result are reported, e.g.…”

Section: Benchmark Resultsmentioning

confidence: 84%

Conditional Prior Networks for Optical Flow

Yang

Soatto

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Classical computation of optical flow involves generic priors (regularizers) that capture rudimentary statistics of images, but not long-range correlations or semantics. On the other hand, fully supervised methods learn the regularity in the annotated data, without explicit regularization and with the risk of overfitting. We seek to learn richer priors on the set of possible flows that are statistically compatible with an image. Once the prior is learned in a supervised fashion, one can easily learn the full map to infer optical flow directly from two or more images, without any need for (additional) supervision. We introduce a novel architecture, called Conditional Prior Network (CPN), and show how to train it to yield a conditional prior. When used in conjunction with a simple optical flow architecture, the CPN beats all variational methods and all unsupervised learning-based ones using the same data term. It performs comparably to fully supervised ones, that however are fine-tuned to a particular dataset. Our method, on the other hand, performs well even when transferred between datasets.

show abstract

Section: Benchmark Resultsmentioning

confidence: 84%

Conditional Prior Networks for Optical Flow

Yang

Soatto

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Upsampling cell. Several hand-designed encoderdecoder architectures have emerged [2,27,73,76] which incorporate the above architecture design choices. Typically such methods propose decoding modules which apply architectural blocks (ShuffleNet [72], DenseNet [31] block, etc).…”

Section: Darts For Dense Predictionmentioning

confidence: 99%

AutoDispNet: Improving Disparity Estimation With AutoML

Saikia

Marrakchi

Zela

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Much research work in computer vision is being spent on optimizing existing network architectures to obtain a few more percentage points on benchmarks. Recent AutoML approaches promise to relieve us from this effort. However, they are mainly designed for comparatively smallscale classification tasks. In this work, we show how to use and extend existing AutoML techniques to efficiently optimize large-scale U-Net-like encoder-decoder architectures. In particular, we leverage gradient-based neural architecture search and Bayesian optimization for hyperparameter search. The resulting optimization does not require a large company-scale compute cluster. We show results on disparity estimation that clearly outperform the manually optimized baseline and reach state-of-the-art performance.

show abstract

“…The first attempt of a deep optical flow estimation network, FlowNet [17], proposed two networks, namely FlowNetS and FlowNetC, and greatly improved the runtime of previous work. Zhu et al [18] developed an optical flow estimation method called DenseNet by extending a deep network for image classification, and demonstrated that it outperforms other unsupervised methods. FlowNet 2.0 [19] is a follow-up paper of FlowNet [17].…”

Section: Optical Flow Estimationmentioning

confidence: 99%

“…Therefore, we can expect that a better understanding of the images results in a more accurate matching. As shown in [18], in optical flow estimation, feature extractors trained on image classification tasks are recommendable for unsupervised learning.…”

Section: A Stronger Feature Extractorsmentioning

confidence: 99%

Improved Optical Flow for Gesture-based Human-robot Interaction

Chang

Tejero-de-Pablos

Harada

2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Gesture interaction is a natural way of communicating with a robot as an alternative to speech. Gesture recognition methods leverage optical flow in order to understand human motion. However, while accurate optical flow estimation (i.e., traditional) methods are costly in terms of runtime, fast estimation (i.e., deep learning) methods' accuracy can be improved. In this paper, we present a pipeline for gesture-based human-robot interaction that uses a novel optical flow estimation method in order to achieve an improved speed-accuracy trade-off. Our optical flow estimation method introduces four improvements to previous deep learning-based methods: strong feature extractors, attention to contours, midway features, and a combination of these three. This results in a better understanding of motion, and a finer representation of silhouettes. In order to evaluate our pipeline, we generated our own dataset, MIBURI, which contains gestures to command a house service robot. In our experiments, we show how our method improves not only optical flow estimation, but also gesture recognition, offering a speed-accuracy trade-off more realistic for practical robot applications.

show abstract

DenseNet for dense flow

Cited by 219 publications

References 26 publications

Conditional Prior Networks for Optical Flow

Conditional Prior Networks for Optical Flow

AutoDispNet: Improving Disparity Estimation With AutoML

Improved Optical Flow for Gesture-based Human-robot Interaction

Contact Info

Product

Resources

About