activity
20192021
most citedPano3D: A Holistic Benchmark and a Solid Baseline for Depth Estimation

51 citations · 54 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2021

Towards Full-to-Empty Room Generation with Structure-Aware Feature Encoding and Soft Semantic Region-Adaptive Normalization

Vasileios Gkitsas, Nikolaos Zioulis, Vladimiros Sterzentsenko +2

The task of transforming a furnished room image into a background-only is extremely challenging since it requires making large changes regarding the scene context while still prese…

cs.CV2021★ 51 cited

Pano3D: A Holistic Benchmark and a Solid Baseline for Depth Estimation

Georgios Albanis, Nikolaos Zioulis, Petros Drakoulis +5

Pano3D is a new benchmark for depth estimation from spherical panoramas. It aims to assess performance across all depth estimation traits, the primary direct depth estimation perfo…

cs.CV2021★ 1 cited

PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes

V. Gkitsas, V. Sterzentsenko, N. Zioulis +2

The rising availability of commercial cameras that democratize indoor scanning, has increased the interest for novel applications, such as interior space re-design. Dim…

cs.CV2020

Deep Lighting Environment Map Estimation from Spherical Panoramas

Vasileios Gkitsas, Nikolaos Zioulis, Federico Alvarez +2

Estimating a scene's lighting is a very important task when compositing synthetic content within real environments, with applications in mixed reality and post-production. In this…

cs.CV2019★ 2 cited

Restyling Data: Application to Unsupervised Domain Adaptation

Vasileios Gkitsas, Antonis Karakottas, Nikolaos Zioulis +2

Machine learning is driven by data, yet while their availability is constantly increasing, training data require laborious, time consuming and error-prone labelling or ground truth…

cs.CV2019

Surface Regression with a Hyper-Sphere Loss

Antonis Karakottas, Nikolaos Zioulis, Stamatis Samaras +4

Omnidirectional vision is becoming increasingly relevant as more efficient image acquisition is now possible. However, the lack of annotated datasets has hindered t…