Optical Flow Estimation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

10 leaderboard tables shown for this task, 10 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

35 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 35 until expanded.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 795 papers with code (2,184 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
  7 Sep 2017 21 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow.
• FlowNet: Learning Optical Flow with Convolutional Networks
  26 Apr 2015 18 repositories listed Syntology ran 1 of 20 samples · 19 unverified
  Optical flow estimation has not been among the tasks where CNNs were successful.
• RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
  26 Mar 2020 17 repositories listed Syntology ran 40 of 66 samples · 26 unverified · 17 pointer-only (licence)
  RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes.
• RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation
  12 Nov 2020 13 repositories listed Syntology ran 19 of 26 samples · 7 unverified · 16 pointer-only (licence)
  We propose RIFE, a Real-time Intermediate Flow Estimation algorithm for Video Frame Interpolation (VFI).
• FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
  6 Dec 2016 12 repositories listed Syntology ran 2 of 21 samples · 19 unverified · 3 pointer-only (licence)
  Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
• Perceiver IO: A General Architecture for Structured Inputs & Outputs
  30 Jul 2021 9 repositories listed Syntology ran 7 of 11 samples · 4 unverified
  A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
• Optical Flow Estimation using a Spatial Pyramid Network
  3 Nov 2016 8 repositories listed
  We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning.
• Two-Stream Convolutional Networks for Action Recognition in Videos
  9 Jun 2014 7 repositories listed Syntology ran 1 of 7 samples · 6 unverified · 2 pointer-only (licence)
  Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art.
• Semantic Flow for Fast and Accurate Scene Parsing
  24 Feb 2020 6 repositories listed Syntology ran 1 of 8 samples · 7 unverified · 1 pointer-only (licence)
  A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation.
• Video Frame Interpolation via Adaptive Separable Convolution
  5 Aug 2017 6 repositories listed
  Our method develops a deep fully convolutional neural network that takes two input frames and estimates pairs of 1D kernels for all pixels simultaneously.
• What Matters in Unsupervised Optical Flow
  8 Jun 2020 5 repositories listed Syntology ran 1 of 17 samples · 16 unverified
  We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective.
• Attention-guided Network for Ghost-free High Dynamic Range Imaging
  23 Apr 2019 5 repositories listed
  Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.
• Depth-Aware Video Frame Interpolation
  1 Apr 2019 5 repositories listed Syntology ran 3 of 15 samples · 12 unverified
  The proposed model then warps the input frames, depth maps, and contextual features based on the optical flow and local interpolation kernels for synthesizing the output frame.
• Representation Flow for Action Recognition
  2 Oct 2018 5 repositories listed
  Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel within a convolutional neural network for action recognition.
• Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
  30 Nov 2017 5 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  Finally, the two input images are warped and linearly fused to form each intermediate frame.
• Deep multi-scale video prediction beyond mean square error
  17 Nov 2015 5 repositories listed Syntology ran 2 of 10 samples · 8 unverified
  Learning to predict future images from a video sequence involves the construction of an internal representation that models the image evolution accurately, and therefore, to some degree, its content and dynamics.
• BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
  27 Jul 2023 4 repositories listed Syntology ran 7 of 10 samples · 3 unverified · 10 pointer-only (licence)
  In the field of phase change phenomena, the lack of accessible and diverse datasets suitable for machine learning (ML) training poses a significant challenge.
• GMFlow: Learning Optical Flow via Global Matching
  26 Nov 2021 4 repositories listed Syntology ran 3 of 19 samples · 16 unverified
  Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the…
• Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
  10 Mar 2021 4 repositories listed
  The code and protocols for our benchmark and algorithm are available at https://github.
• Learning Accurate Dense Correspondences and When to Trust Them
  5 Jan 2021 4 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Establishing dense correspondences between a pair of images is an important and general problem.
• Towards Better Generalization: Joint Depth-Pose Learning without PoseNet
  3 Apr 2020 4 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  In this work, we tackle the essential problem of scale inconsistency for self-supervised joint depth-pose learning.
• Temporal Interlacing Network
  17 Jan 2020 4 repositories listed Syntology ran 12 of 25 samples · 13 unverified
  In this way, a heavy temporal model is replaced by a simple interlacing operator.
• DVC: An End-to-end Deep Video Compression Framework
  30 Nov 2018 4 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 3 pointer-only (licence)
  Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information.
• Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection
  21 Nov 2018 4 repositories listed
  Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction.
• DGC-Net: Dense Geometric Correspondence Network
  19 Oct 2018 4 repositories listed
  This paper addresses the challenge of dense pixel correspondence estimation between two images.
• YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
  3 Sep 2018 4 repositories listed
  End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i.
• LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
  18 May 2018 4 repositories listed
  FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation.
• Im2Flow: Motion Hallucination from Static Images for Action Recognition
  12 Dec 2017 4 repositories listed
  Second, we show the power of hallucinated flow for recognition, successfully transferring the learned motion into a standard two-stream network for activity recognition.
• Video Enhancement with Task-Oriented Flow
  24 Nov 2017 4 repositories listed
  Many video enhancement algorithms rely on optical flow to register frames in a video sequence.
• Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
  12 Jun 2017 4 repositories listed Syntology ran 9 of 10 samples · 1 unverified · 5 pointer-only (licence)
  To address these problems, we propose both a new model and a benchmark for precipitation nowcasting.

Syntology lines on 19 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.