Csaba Benedek — accepted AI-conference papers

2023

ST-DepthNet: A Spatio-Temporal Deep Network for Depth Completion Using a Single Non-Repetitive Circular Scanning Lidar

Örkény Zováthi, Balázs Pálffy, Zsolt Jankó, Csaba Benedek

RA-L 2023

In this paper, we propose a novel depth image completion technique based on sparse consecutive measurements of a non-repetitive circular scanning (NRCS) Lidar, demonstrating the capabilities of a new, compact, and accessible sensor technology for dense range mapping of highly dynamic scenes. Our dee

Cited by 6 Source ↗Scholar ↗

2021

ChangeGAN: A Deep Network for Change Detection in Coarsely Registered Point Clouds

Balázs Nagy, Lóránt Kovács, Csaba Benedek

RA-L 2021

In this letter we introduce a novel change detection approach called ChangeGAN for coarsely registered point clouds in complex street-level urban environment. Our generative adversarial network-like (GAN) architecture compounds Siamese-style feature extraction, U-net-like use of multiscale features,

Cited by 22 Source ↗Scholar ↗