About

Optical Flow Estimation is the problem of finding pixel-wise motions between consecutive images.

Source: Devon: Deformable Volume Network for Learning Optical Flow

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

ECCV 2020 tensorflow/models

We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.

OPTICAL FLOW ESTIMATION PANOPTIC SEGMENTATION PATCH MATCHING SCENE SEGMENTATION

What Matters in Unsupervised Optical Flow

ECCV 2020 google-research/google-research

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.

OCCLUSION HANDLING OPTICAL FLOW ESTIMATION

Depth-Aware Video Frame Interpolation

CVPR 2019 baowenbo/DAIN

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.

OPTICAL FLOW ESTIMATION VIDEO FRAME INTERPOLATION

Semantic Flow for Fast and Accurate Scene Parsing

ECCV 2020 donnyyou/torchcv

A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation.

OPTICAL FLOW ESTIMATION REAL-TIME SEMANTIC SEGMENTATION SCENE PARSING

Deep Flow-Guided Video Inpainting

CVPR 2019 nbei/Deep-Flow-Guided-Video-Inpainting

Then the synthesized flow field is used to guide the propagation of pixels to fill up the missing regions in the video.

OPTICAL FLOW ESTIMATION VIDEO FIXED REGION INPAINTING VIDEO INPAINTING YOUTUBE-VOS

FlowNet: Learning Optical Flow with Convolutional Networks

ICCV 2015 msracver/Deep-Feature-Flow

Optical flow estimation has not been among the tasks where CNNs were successful.

OPTICAL FLOW ESTIMATION

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

ECCV 2020 princeton-vl/RAFT

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.

OPTICAL FLOW ESTIMATION

A Fusion Approach for Multi-Frame Optical Flow Estimation

23 Oct 2018NVlabs/PWC-Net

To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account.

OPTICAL FLOW ESTIMATION