Browse SoTA > Computer Vision > Optical Flow Estimation

Optical Flow Estimation

192 papers with code · Computer Vision

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

Source: Devon: Deformable Volume Network for Learning Optical Flow

Benchmarks

Latest papers with code

Robust Ego and Object 6-DoF Motion Estimation and Tracking

28 Jul 2020halajun/vdo_slam

The problem of tracking self-motion as well as motion of objects in the scene using information from a camera is known as multi-body visual odometry and is a challenging task.

AUTONOMOUS DRIVING MOTION ESTIMATION OPTICAL FLOW ESTIMATION VISUAL ODOMETRY

76
28 Jul 2020

Unsupervised Learning of Particle Image Velocimetry

28 Jul 2020erizmr/UnLiteFlowNet-PIV

Recently, the development of deep learning based methods has inspired new approaches to tackle the PIV problem.

OPTICAL FLOW ESTIMATION

1
28 Jul 2020

LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

18 Jul 2020twhui/LiteFlowNet3

The keys to success lie in the use of cost volume and coarse-to-fine flow inference.

OPTICAL FLOW ESTIMATION

28
18 Jul 2020

Low-light Environment Neural Surveillance

2 Jul 2020mcgridles/LENS

The system uses a low-light video feed processed in real-time by an optical-flow network, spatial and temporal networks, and a Support Vector Machine to identify shootings, assaults, and thefts.

ACTION RECOGNITION OPTICAL FLOW ESTIMATION

3
02 Jul 2020

Learning Geocentric Object Pose in Oblique Monocular Images

CVPR 2020 pubgeo/monocular-geocentric-pose

An object's geocentric pose, defined as the height above ground and orientation with respect to gravity, is a powerful representation of real-world structure for object detection, segmentation, and localization tasks using RGBD images.

OBJECT DETECTION OPTICAL FLOW ESTIMATION SEMANTIC SEGMENTATION

11
01 Jul 2020

Creating Artificial Modalities to Solve RGB Liveness

29 Jun 2020AlexanderParkin/CASIA-SURF_CeFA

Special cameras that provide useful features for face anti-spoofing are desirable, but not always an option.

FACE ANTI-SPOOFING OPTICAL FLOW ESTIMATION

45
29 Jun 2020

Motion Representation Using Residual Frames with 3D CNN

21 Jun 2020BestJuly/VCP

In this paper, we propose a fast but effective way to extract motion features from videos utilizing residual frames as the input data in 3D ConvNets.

ACTION RECOGNITION OPTICAL FLOW ESTIMATION

1
21 Jun 2020

What Matters in Unsupervised Optical Flow

8 Jun 2020google-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.

OPTICAL FLOW ESTIMATION

12,016
08 Jun 2020

TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution

CVPR 2020 YapengTian/TDAN-VSR

Video super-resolution (VSR) aims to restore a photo-realistic high-resolution (HR) video frame from both its corresponding low-resolution (LR) frame (reference frame) and multiple neighboring frames (supporting frames).

OPTICAL FLOW ESTIMATION VIDEO SUPER-RESOLUTION

163
01 Jun 2020