Victor Czech — accepted AI-conference papers

2025

Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation

Tim Elsner, Paula Usinger, Julius Nehring-Wirxel, Gregor Kobsik, Victor Czech, Yanjiang He +2

ICCV 2025poster

In language processing, transformers benefit greatly from characters being condensed into word fragments, building outputs from a larger vocabulary of bigger pieces. This is often done with Byte Pair Encoding. In the context of images, tokenisation of visual data is usually limited to regular grids…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Retargeting Visual Data with Deformation Fields

Tim Elsner*, Julia Berger, Tong Wu, Victor Czech, Lin Gao, Leif Kobbelt

ECCV 2024poster

"Seam carving is an image editing method that enables content-aware resizing, including operations like removing objects. However, the seam-finding strategy based on dynamic programming or graph-cut limits its applications to broader visual data formats and degrees of freedom for editing. Our observ…

Cited by 2 Source ↗PDF ↗Scholar ↗