Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling

• URL: http://arxiv.org/abs/2511.13478v1
• Date: Mon, 17 Nov 2025 15:16:13 GMT
• Title: Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling
• Authors: Adam Hazimeh, Ke Wang, Mark Collier, Gilles Baechler, Efi Kokiopoulou, Pascal Frossard,
• Abstract summary: We introduce SliDer, a novel framework that uses Vision-Language Models to derender slide images as compact and editable SVG representations.<n>SliDer achieves a reconstruction LPIPS of 0.069 and is favored by human evaluators in 82.9% of cases compared to the strongest zero-shot VLM baseline.
• Score: 32.22298939812003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimedia documents such as slide presentations and posters are designed to be interactive and easy to modify. Yet, they are often distributed in a static raster format, which limits editing and customization. Restoring their editability requires converting these raster images back into structured vector formats. However, existing geometric raster-vectorization methods, which rely on low-level primitives like curves and polygons, fall short at this task. Specifically, when applied to complex documents like slides, they fail to preserve the high-level structure, resulting in a flat collection of shapes where the semantic distinction between image and text elements is lost. To overcome this limitation, we address the problem of semantic document derendering by introducing SliDer, a novel framework that uses Vision-Language Models (VLMs) to derender slide images as compact and editable Scalable Vector Graphic (SVG) representations. SliDer detects and extracts attributes from individual image and text elements in a raster input and organizes them into a coherent SVG format. Crucially, the model iteratively refines its predictions during inference in a process analogous to human design, generating SVG code that more faithfully reconstructs the original raster upon rendering. Furthermore, we introduce Slide2SVG, a novel dataset comprising raster-SVG pairs of slide documents curated from real-world scientific presentations, to facilitate future research in this domain. Our results demonstrate that SliDer achieves a reconstruction LPIPS of 0.069 and is favored by human evaluators in 82.9% of cases compared to the strongest zero-shot VLM baseline.

Related papers

• VecGlypher: Unified Vector Glyph Generation with Language Models [49.18215716168074]
  VecGlypher generates high-fidelity vector glyphs directly from text descriptions or image exemplars.<n>VecGlypher autoregressively emits SVG path tokens, avoiding intermediates and a target character.
  arXiv  Detail & Related papers  (2026-02-25T00:27:23Z)
• SVGen: Interpretable Vector Graphics Generation with Large Language Models [61.62816031675714]
  We introduce SVG-1M, a large-scale dataset of high-quality SVGs paired with natural language descriptions.<n>We create well-aligned Text to SVG training pairs, including a subset with Chain of Thought annotations for enhanced semantic guidance.<n>Based on this dataset, we propose SVGen, an end-to-end model that generates SVG code from natural language inputs.
  arXiv  Detail & Related papers  (2025-08-06T15:00:24Z)
• NeuralSVG: An Implicit Representation for Text-to-Vector Generation [54.4153300455889]
  We propose NeuralSVG, an implicit neural representation for generating vector graphics from text prompts.<n>To encourage a layered structure in the generated SVG, we introduce a dropout-based regularization technique.<n>We demonstrate that NeuralSVG outperforms existing methods in generating structured and flexible SVG.
  arXiv  Detail & Related papers  (2025-01-07T18:50:06Z)
• Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision [20.325246638505714]
  We introduce GRIMOIRE, a text-guided generative model that learns to map images onto a discrete codebook by reconstructing them as vector shapes. Unlike existing models that require direct supervision from data, GRIMOIRE learns using only image supervision which opens up vector generative modeling to significantly more data.
  arXiv  Detail & Related papers  (2024-10-08T12:41:31Z)
• SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis [66.44553285020066]
  SuperSVG is a superpixel-based vectorization model that achieves fast and high-precision image vectorization. We propose a two-stage self-training framework, where a coarse-stage model is employed to reconstruct the main structure and a refinement-stage model is used for enriching the details. Experiments demonstrate the superior performance of our method in terms of reconstruction accuracy and inference time compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-06-14T07:43:23Z)
• Visually Descriptive Language Model for Vector Graphics Reasoning [76.42082386029206]
  We propose the Visually Descriptive Language Model (VDLM) to bridge the gap between low-level visual perception and high-level language reasoning.<n>We show that VDLM significantly improves state-of-the-art LMMs like GPT-4o on various multimodal perception and reasoning tasks.
  arXiv  Detail & Related papers  (2024-04-09T17:30:18Z)
• SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout [14.824205628841158]
  This work introduces a novel end-to-end framework for the creation of vector graphics depicting entire scenes from textual descriptions. SVGCraft is optimized using a pre-trained encoder and LPIPS loss with opacity modulation to maximize similarity. It is demonstrated to surpass prior works in abstraction, recognizability, and detail.
  arXiv  Detail & Related papers  (2024-03-30T16:43:40Z)
• Text-Guided Vector Graphics Customization [31.41266632288932]
  We propose a novel pipeline that generates high-quality customized vector graphics based on textual prompts. Our method harnesses the capabilities of large pre-trained text-to-image models. We evaluate our method using multiple metrics from vector-level, image-level and text-level perspectives.
  arXiv  Detail & Related papers  (2023-09-21T17:59:01Z)
• VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models [82.93345261434943]
  We show that a text-conditioned diffusion model trained on pixel representations of images can be used to generate SVG-exportable vector graphics. Inspired by recent text-to-3D work, we learn an SVG consistent with a caption using Score Distillation Sampling. Experiments show greater quality than prior work, and demonstrate a range of styles including pixel art and sketches.
  arXiv  Detail & Related papers  (2022-11-21T10:04:27Z)
• Towards Layer-wise Image Vectorization [57.26058135389497]
  We propose Layerwise Image Vectorization, namely LIVE, to convert images to SVGs and simultaneously maintain its image topology. Live generates compact forms with layer-wise structures that are semantically consistent with human perspective. Live initiates human editable SVGs for both designers and can be used in other applications.
  arXiv  Detail & Related papers  (2022-06-09T17:55:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.