3 papers
cs.CV2026
SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction
Daniel Woortmann, Tanguy Magne, Olga Sorkine-Hornung
Deep learning models have become the standard tool for document rectification and illumination correction, yet their performance is fundamentally bound by their training data. For…
cs.GR2026
Single-Line Drawing Generation via Semantics-Driven Optimization
Tanguy Magne, Alexandre Binninger, Ruben Wiersma +1
Line drawings are a highly expressive art form that requires the artist to abstract and distill the essence of their subject. We present the first semantics-driven method for autom…
cs.CV2023
UVDoc: Neural Grid-based Document Unwarping
Floor Verhoeven, Tanguy Magne, Olga Sorkine-Hornung
Restoring the original, flat appearance of a printed document from casual photographs of bent and wrinkled pages is a common everyday problem. In this paper we propose a novel meth…