Open source tools developed by VCL


A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation 


Spherical Panorama Diminished Reality for Indoor Scenes

A multimodal UAV assistant dataset

Photorealistic UAV-Assistant Dataset Synthesis for 3D Pose Estimation via a Smooth Silhouette Loss

Markerless volumetric (multi-sensor) alignment for depth sensors

Contains a variety of human activities simultaneously captured by a professional marker-based MoCap, a volumetric capture and an audio recording system.

Self-Supervised 360o Depth Estimation

3D Vision Indoors Spherical Panoramas

Pre-trained models for Intel RealSense D415

Deep Lighting Environment Map Estimation from Spherical Panoramas

Code accompanying the paper "360 Surface Regression with a Hyper-Sphere Loss", 3DV 2019

Blending the real and the virtual through real-time volumetric capture

Fast and precise hippocampus segmentation through deep convolutional neural network ensembles and transfer learning

A multi-sensor capture system for free viewpoint video

The data were obtained using two different capturing setups, both with multiple Kinects2 in a circular configuration

Three different capturing setups are realized, each with 5 Kinects in a circular configuration

The CERTH/ITI dataset of Kinect-based 3D scans

The dataset was recorded with a multi-Kinect2 capturing setup in a circular configuration

© Copyright 2022 VCL - All Rights Reserved

Site was started with Mobirise