Occlusion Handling

11 papers with code • 0 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

AeroRIT: A New Scene for Hyperspectral Image Analysis

aneesh3108/AeroRIT 17 Dec 2019

We investigate applying convolutional neural network (CNN) architecture to facilitate aerial hyperspectral scene understanding and present a new hyperspectral dataset-AeroRIT-that is large enough for CNN training.

EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Association

EmbodiedVision/emfusion ICCV 2019

The majority of approaches for acquiring dense 3D environment maps with RGB-D cameras assumes static environments or rejects moving objects as outliers.

How to track your dragon: A Multi-Attentional Framework for real-time RGB-D 6-DOF Object Pose Tracking

ismarou/How_to_track_your_Dragon 21 Apr 2020

We present a novel multi-attentional convolutional architecture to tackle the problem of real-time RGB-D 6D object pose tracking of single, known objects.

What Matters in Unsupervised Optical Flow

google-research/google-research ECCV 2020

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.

Level Set Stereo for Cooperative Grouping with Occlusion

jialiangw/levelsetstereo 29 Jun 2020

We introduce an energy and level-set optimizer that improves boundaries by encoding the essential geometry of occlusions: The spatial extent of an occlusion must equal the amplitude of the disparity jump that causes it.

Symmetric Parallax Attention for Stereo Image Super-Resolution

YingqianWang/iPASSR 7 Nov 2020

Although recent years have witnessed the great advances in stereo image super-resolution (SR), the beneficial information provided by binocular systems has not been fully used.

Simple online and real-time tracking with occlusion handling

mhnasseri/sort_oh 6 Mar 2021

In contrast, there are algorithms that only use motion cues to increase speed, especially for online applications.

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

lkeab/BCNet CVPR 2021

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries.

TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction

ethz-asl/tsdf-plusplus 16 May 2021

The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction.

Level Set Binocular Stereo with Occlusions

jialiangw/levelsetstereo 8 Sep 2021

Localizing stereo boundaries and predicting nearby disparities are difficult because stereo boundaries induce occluded regions where matching cues are absent.