UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning

• URL: http://arxiv.org/abs/2012.00212v1
• Date: Tue, 1 Dec 2020 01:57:46 GMT
• Title: UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
• Authors: Kunming Luo, Chuan Wang, Shuaicheng Liu, Haoqiang Fan, Jue Wang, Jian Sun
• Abstract summary: We present an unsupervised learning approach for optical flow estimation. We design a self-guided upsample module to tackle the blur problem caused by bilinear upsampling between pyramid levels. We propose a pyramid distillation loss to add supervision for intermediate levels via distilling the finest flow as pseudo labels.
• Score: 34.580309867067946
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present an unsupervised learning approach for optical flow estimation by improving the upsampling and learning of pyramid network. We design a self-guided upsample module to tackle the interpolation blur problem caused by bilinear upsampling between pyramid levels. Moreover, we propose a pyramid distillation loss to add supervision for intermediate levels via distilling the finest flow as pseudo labels. By integrating these two components together, our method achieves the best performance for unsupervised optical flow learning on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015. In particular, we achieve EPE=1.4 on KITTI 2012 and F1=9.38% on KITTI 2015, which outperform the previous state-of-the-art methods by 22.2% and 15.7%, respectively.

Related papers

• DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow [7.73554718719193]
  We propose a novel Patchmatch-based framework to work on high-resolution optical flow estimation. It can get high-precision results with lower memory benefiting from propagation and local search of Patchmatch. Our method ranks first on all the metrics on the popular KITTI2015 benchmark, and ranks second on EPE on the Sintel clean benchmark among published optical flow methods.
  arXiv  Detail & Related papers  (2022-04-01T10:13:59Z)
• Detail Preserving Residual Feature Pyramid Modules for Optical Flow [3.3301533805099357]
  Residual Feature Pyramid Module (RFPM) retains important details in the feature map without changing the overall iterative refinement design of the optical flow estimation. Results show that our RFPM visibly reduces flow errors and improves state-of-art performance in the clean pass of Sintel.
  arXiv  Detail & Related papers  (2021-07-23T01:53:04Z)
• Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation [71.76008290101214]
  DistillFlow is a knowledge distillation approach to learning optical flow. It achieves state-of-the-art unsupervised learning performance on both KITTI and Sintel datasets. Our models ranked 1st among all monocular methods on the KITTI 2015 benchmark, and outperform all published methods on the Sintel Final benchmark.
  arXiv  Detail & Related papers  (2021-06-08T09:13:34Z)
• ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling [26.868635622137106]
  We present an unsupervised optical flow estimation method by proposing an adaptive pyramid sampling in the deep pyramid network. Our method achieves the best performance for unsupervised optical flow estimation on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015.
  arXiv  Detail & Related papers  (2021-04-08T07:22:35Z)
• Learning Affinity-Aware Upsampling for Deep Image Matting [83.02806488958399]
  We show that learning affinity in upsampling provides an effective and efficient approach to exploit pairwise interactions in deep networks. In particular, results on the Composition-1k matting dataset show that A2U achieves a 14% relative improvement in the SAD metric against a strong baseline. Compared with the state-of-the-art matting network, we achieve 8% higher performance with only 40% model complexity.
  arXiv  Detail & Related papers  (2020-11-29T05:09:43Z)
• What Matters in Unsupervised Optical Flow [51.45112526506455]
  We compare and analyze a set of key components in unsupervised optical flow. We construct a number of novel improvements to unsupervised flow models. We present a new unsupervised flow technique that significantly outperforms the previous state-of-the-art.
  arXiv  Detail & Related papers  (2020-06-08T19:36:26Z)
• ScopeFlow: Dynamic Scene Scoping for Optical Flow [94.42139459221784]
  We propose to modify the common training protocols of optical flow. The improvement is based on observing the bias in sampling challenging data. We find that both regularization and augmentation should decrease during the training protocol.
  arXiv  Detail & Related papers  (2020-02-25T09:58:49Z)
• FPCR-Net: Feature Pyramidal Correlation and Residual Reconstruction for Optical Flow Estimation [72.41370576242116]
  We propose a semi-supervised Feature Pyramidal Correlation and Residual Reconstruction Network (FPCR-Net) for optical flow estimation from frame pairs. It consists of two main modules: pyramid correlation mapping and residual reconstruction. Experiment results show that the proposed scheme achieves the state-of-the-art performance, with improvement by 0.80, 1.15 and 0.10 in terms of average end-point error (AEE) against competing baseline methods.
  arXiv  Detail & Related papers  (2020-01-17T07:13:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.