IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework

• URL: http://arxiv.org/abs/2603.09312v1
• Date: Tue, 10 Mar 2026 07:44:51 GMT
• Title: IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework
• Abstract summary: Existing text-to-SVG generation methods do not incorporate visual perception of the final rendered image.<n>We propose an Introspective SVG Generation Framework (IntroSVG)<n>We show that our method achieves state-of-the-art performance across several key evaluation metrics.
• Score: 20.964700751378547
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scalable Vector Graphics (SVG) are central to digital design due to their inherent scalability and editability. Despite significant advancements in content generation enabled by Visual Language Models (VLMs), existing text-to-SVG generation methods are limited by a core challenge: the autoregressive training process does not incorporate visual perception of the final rendered image, which fundamentally constrains generation quality. To address this limitation, we propose an Introspective SVG Generation Framework (IntroSVG). At its core, the framework instantiates a unified VLM that operates in a closed loop, assuming dual roles of both generator and critic. Specifically, through Supervised Fine-Tuning (SFT), the model learns to draft SVGs and to provide feedback on their rendered outputs; moreover, we systematically convert early-stage failures into high-quality error-correction training data, thereby enhancing model robustness. Subsequently, we leverage a high-capacity teacher VLM to construct a preference dataset and further align the generator's policy through Direct Preference Optimization (DPO). During inference, the optimized generator and critic operate collaboratively in an iterative "generate-review-refine" cycle, starting from imperfect intermediate drafts to autonomously improve output quality. Experimental results demonstrate that our method achieves state-of-the-art performance across several key evaluation metrics, generating SVGs with more complex structures, stronger semantic alignment, and greater editability. These results corroborate the effectiveness of incorporating explicit visual feedback into the generation loop.

Related papers

• SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation [62.7676301168359]
  We introduce textbfours, a human-aligned evaluation framework for text-to-SVG generation.<n>We first show that CLIP-based scores barely react to the errors SVG generators actually make, such as wrong colors, counts, and spatial relations.<n>We then introduce a human-annotated dataset for textitSemantic Alignment, measuring how faithfully a generated SVG reflects its caption.
  arXiv  Detail & Related papers  (2026-09-03T13:12:37Z)
• Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMs [50.541990269155484]
  We evaluate whether inference-time methods can unlock SVG generation capabilities in off-the-shelf vision-language models (VLMs)<n>Our results highlight both the promise and current limitations of using inference-time methods to adapt general-purpose VLMs for SVG generation.
  arXiv  Detail & Related papers  (2026-08-26T00:51:10Z)
• RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG Generation [2.1124849856688064]
  RefineSVG is a single-step closed-loop visual feedback framework.<n>It enables multimodal large language models (MLLMs) to perform high-fidelity image-to-SVG generation through self-correction.
  arXiv  Detail & Related papers  (2026-07-30T05:30:14Z)
• GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation [29.64540884592851]
  We introduce GeoSVG-RL, a specialized reinforcement learning framework designed for layout-constrained text-to-SVG generation.<n>The model first produces a structured layout plan that serves as a geometric contract for the subsequent generation of the SVG code.<n>GeoSVG-RL achieves substantial gains in structural reliability, particularly in arrow-anchor accuracy and text-in-box rates.
  arXiv  Detail & Related papers  (2026-05-25T05:56:44Z)
• Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback [29.19392406217364]
  We propose a novel generation paradigm that reformulates SVG synthesis as a step-wise, visual-context-aware process.<n>By rendering intermediate code states into a cumulative canvas, the model explicitly observes the evolving visual context at each step.<n>We show that applying this visual loop naively to off-the-shelf models is suboptimal due to their inability to leverage incremental visual-code mappings.
  arXiv  Detail & Related papers  (2026-04-22T16:15:28Z)
• Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure [57.89872230703339]
  We introduce a framework that recovers the semantic structure required for reliable SVG animation.<n>By reorganizing SVGs into semantic groups, our approach enables VLMs to produce animations with far greater coherence.
  arXiv  Detail & Related papers  (2025-12-16T12:03:46Z)
• SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder [90.28800377462197]
  We propose SVG-T2I to support high-quality text-to-image synthesis directly in the VFM feature domain.<n>By leveraging a standard text-to-image diffusion pipeline, SVG-T2I achieves competitive performance, reaching 0.75 on GenEval and 85.78 on DPG-Bench.<n>We fully open-source the project, including the autoencoder and generation model, together with their training, inference, evaluation pipelines, and pre-trained weights, to facilitate further research in representation-driven visual generation.
  arXiv  Detail & Related papers  (2025-12-12T17:45:03Z)
• SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation [47.390332111383294]
  We present SVGThinker, a reasoning-driven framework that aligns the production of SVG code with the visualization process.<n>Our pipeline first renders each primitive in sequence and uses a multimodal model to annotate the image and code.<n> Experiments against state-of-the-art baselines show that SVGThinker produces more stable, editable, and higher-quality SVGs.
  arXiv  Detail & Related papers  (2025-09-29T05:25:00Z)
• 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)
• Rendering-Aware Reinforcement Learning for Vector Graphics Generation [15.547843461605746]
  We introduce RLRF(Reinforcement Learning from Rendering Feedback), an RL method that enhances SVG generation in vision-language models (VLMs)<n>Given an input image, the model generates SVG roll-outs that are rendered and compared to the original image to compute a reward.<n>This visual fidelity feedback guides the model toward producing more accurate, efficient, and semantically coherent SVGs.
  arXiv  Detail & Related papers  (2025-05-27T06:56:00Z)
• OmniSVG: A Unified Scalable Vector Graphics Generation Model [69.59073636922287]
  We propose OmniSVG, a unified framework that leverages pre-trained Vision-Language Models for end-to-end multimodal SVG generation.<n>By parameterizing SVG commands and coordinates into discrete tokens, OmniSVG decouples structural logic from low-level geometry for efficient training while maintaining the synthesis of complex SVG structure.<n>We introduce MMSVG-2M, a multimodal dataset with two million annotated SVG assets, along with a standardized evaluation protocol for conditional SVG generation tasks.
  arXiv  Detail & Related papers  (2025-04-08T17:59:49Z)
• 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)
• SVGDreamer: Text Guided SVG Generation with Diffusion Model [31.76771064173087]
  We propose a novel text-guided vector graphics synthesis method called SVGDreamer.<n>SIVE process enables decomposition of synthesis into foreground objects and background.<n>VPSD approach addresses issues of shape over-smoothing, color over-saturation, limited diversity, and slow convergence.
  arXiv  Detail & Related papers  (2023-12-27T08:50:01Z)

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.