arXiv subjects

Christian Franke

Publications and source records attributed to Christian Franke.

3 recordsLinked to original sources

arXiv2026

AnchorFlow: Editable SVG Reconstruction via Sparse Anchor Point Fields

Image-to-SVG reconstruction aims to produce vector graphics that are faithful to raster inputs and easy to edit. Existing methods face a structural trade-off in how vector structure is parameterized, including how many paths represent an image and how many anchor points define each path. High-fidelity methods often rely on many paths or densely parameterized curves, whereas overly compact SVG generation may deviate from the input geometry. This issue becomes more pronounced when local raster evidence is imperfect, where boundary-following reconstruction can introduce redundant anchors and fragmented structures. We argue that this trade-off should be addressed at the level of anchor placement, since anchors on Bezier curves define local path structure and strongly affect both accuracy and editability. We propose AnchorFlow, an editable SVG reconstruction framework that models path-level anchor placement with sparse anchor point fields. Given path-like foreground components extracted from a raster image, AnchorFlow predicts an image-conditioned sparse anchor field for each component and resolves it into an ordered Bezier path. Rendering-guided feedback then corrects local structural errors before re-resolution. The recovered paths are then assembled and optimized into the final SVG. Experiments on isolated paths and full images show that AnchorFlow achieves a favorable fidelity-editability trade-off, substantially reducing editable complexity while preserving competitive raster fidelity.

cs.GR↗

arXiv2026

Low peak-power pulse compression in gas-filled Herriott cells in the 2 {\mu}m wavelength range

At laser wavelengths longer than the prominent 1 {\mu}m range of high-power ytterbium-doped lasers, nonlinear phase shifts produced in nonlinear media for spectral broadening and subsequent pulse compression decrease drastically. Consequently, at the 2 {\mu}m wavelength range, the threshold of the applicable peak power for pulse compression in gas-filled multipass cells increases. The common approach of choosing a Herriott multipass cell configuration close to the concentric resonator does not necessarily lead to the highest total nonlinear phase shift, due to a restriction of the total number of reflections on the cell mirrors of a given size. Therefore, an analytical approach is presented here to maximize the nonlinear phase shift for a given set of mirrors, considering lossless and dispersionless propagation. Furthermore, to achieve pulse compression with gas-filled multipass cells for relatively low peak powers at wavelengths around 2 {\mu}m, we developed a high-pressure gas cell and demonstrated experimentally pulse compression in the negative- and positive dispersion regimes, with achieved pulse durations of around 40 fs and 55 fs respectively.

physics.optics↗

arXiv2025

SVG360: Editable Multiview Vector Graphics from a Single SVG

Scalable Vector Graphics are a standard representation for editable visual design, yet they are usually authored as single view two dimensional illustrations. This limits their use in applications that require object level assets to remain coherent when observed, edited, or animated from different viewpoints. We present SVG360, a framework that converts a single input SVG into geometrically and visually consistent multiview SVG assets. The key challenge is that direct per view generation or vectorization produces view dependent regions, fragmented paths, and unstable colors, making the resulting SVGs difficult to edit as a coherent object. SVG360 addresses this problem through a view consistent vectorization pipeline. It first lifts the rasterized input into a view conditioned object representation and renders target views under prescribed cameras. It then propagates part identity across neighboring views using a spatial memory mechanism adapted from video segmentation, establishing consistent region decomposition, path correspondence, and color assignment without task specific retraining. Finally, each view is reconstructed as an editable SVG through structure aware vectorization, where redundant paths are consolidated and local geometry is optimized while preserving boundaries and semantic parts. Experiments on object level SVG assets show that SVG360 improves multiview consistency, reduces path redundancy, and better preserves fine structures compared with direct per view vectorization. By turning a single view SVG into a coherent 360 degree vector asset, SVG360 expands vector graphics from static illustration toward editable multiview content for design, animation, and structured visual editing.

cs.CV↗