Browse > Computer Vision > Optical Flow Estimation

Optical Flow Estimation

143 papers with code ยท Computer Vision

Leaderboards

Latest papers without code

Efficient Semantic Video Segmentation with Per-frame Inference

26 Feb 2020

In semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence.

OPTICAL FLOW ESTIMATION SEMANTIC SEGMENTATION VIDEO SEMANTIC SEGMENTATION

ScopeFlow: Dynamic Scene Scoping for Optical Flow

25 Feb 2020

We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process.

OPTICAL FLOW ESTIMATION

Semantic Flow for Fast and Accurate Scene Parsing

24 Feb 2020

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

OPTICAL FLOW ESTIMATION SCENE PARSING

Feasibility of Video-based Sub-meter Localization on Resource-constrained Platforms

19 Feb 2020

While the satellite-based Global Positioning System (GPS) is adequate for some outdoor applications, many other applications are held back by its multi-meter positioning errors and poor indoor coverage.

OPTICAL FLOW ESTIMATION

SpotNet: Self-Attention Multi-Task Network for Object Detection

13 Feb 2020

We use those segmentation maps inside the network as a self-attention mechanism to weight the feature map used to produce the bounding boxes, decreasing the signal of non-relevant areas.

MULTI-TASK LEARNING OBJECT DETECTION OPTICAL FLOW ESTIMATION

Self-Supervised Object-in-Gripper Segmentation from Robotic Motions

11 Feb 2020

We present a novel technique to automatically generate annotated data for important robotic perception tasks such as object segmentation and 3D object reconstruction using a robot manipulator.

3D OBJECT RECONSTRUCTION CALIBRATION OPTICAL FLOW ESTIMATION SEMANTIC SEGMENTATION

Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition

10 Feb 2020

Wearable cameras are becoming more and more popular in several applications, increasing the interest of the research community in developing approaches for recognizing actions from a first-person point of view.

MOTION SEGMENTATION OPTICAL FLOW ESTIMATION

Predictive online optimisation with applications to optical flow

8 Feb 2020

To prove convergence we need a predictor for the dual variable based on (proximal) gradient flow.

OPTICAL FLOW ESTIMATION

Depth Map Estimation of Dynamic Scenes Using Prior Depth Information

2 Feb 2020

To estimate depth in these scenarios, our algorithm models the dynamic scene motion using independent and rigid motions.

OPTICAL FLOW ESTIMATION