Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback

• URL: http://arxiv.org/abs/2604.20730v2
• Date: Thu, 23 Apr 2026 07:10:08 GMT
• Title: Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
• Abstract summary: 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.
• Score: 29.19392406217364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typically adopt an open-loop "blind drawing" approach, where models generate symbolic code sequences without perceiving intermediate visual outcomes. This methodology severely underutilizes the powerful visual priors embedded in MLLMs vision encoders, treating SVG generation as a disjointed textual sequence modeling task rather than an integrated visuo-spatial one. Consequently, models struggle to reason about partial canvas states and implicit occlusion relationships, which are visually explicit but textually ambiguous. To bridge this gap, we propose Render-in-the-Loop, a novel generation paradigm that reformulates SVG synthesis as a step-wise, visual-context-aware process. By rendering intermediate code states into a cumulative canvas, the model explicitly observes the evolving visual context at each step, leveraging on-the-fly feedback to guide subsequent generation. However, we demonstrate that applying this visual loop naively to off-the-shelf models is suboptimal due to their inability to leverage incremental visual-code mappings. To address this, we first utilize fine-grained path decomposition to construct dense multi-step visual trajectories, and then introduce a Visual Self-Feedback (VSF) training strategy to condition the next primitive generation on intermediate visual states. Furthermore, a Render-and-Verify (RaV) inference mechanism is proposed to effectively filter degenerate and redundant primitives. Our framework, instantiated on a multimodal foundation model, outperforms strong open-weight baselines on the standard MMSVGBench. This result highlights the remarkable data efficiency and generalization capability of our Render-in-the-Loop paradigm for both Text-to-SVG and Image-to-SVG tasks.

Related papers

• 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)
• Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification [80.62512020268626]
  UniAR is a unified autoregressive framework where a single visual tokenizer serves as the key bridge between understanding and generation.<n>UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme.<n>A diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images.
  arXiv  Detail & Related papers  (2026-06-16T17:59:22Z)
• Visual-ERM: Reward Modeling for Visual Equivalence [59.317480168347664]
  Visual Equivalence Reward Model (Visual-ERM) is a multimodal generative reward model that provides fine-grained, interpretable, and task-agnostic feedback.<n>Visual-ERM improves Qwen3-VL-8B-Instruct by +8.4 on chart-to-code and yields consistent gains on table and SVG parsing.<n>VisualCritic-RewardBench (VC-RewardBench) is a benchmark for judging fine-grained image-to-image discrepancies on structured visual data.
  arXiv  Detail & Related papers  (2026-03-13T17:58:14Z)
• IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework [20.964700751378547]
  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.
  arXiv  Detail & Related papers  (2026-03-10T07:44:51Z)
• From Tokens to Numbers: Continuous Number Modeling for SVG Generation [17.597559308984042]
  Continuous Number Modeling (CNM) is an approach that directly models numbers as first-class, continuous values rather than discrete tokens.<n>Our formulation improves training speed by over 30% while maintaining higher fidelity compared to alternative approaches.
  arXiv  Detail & Related papers  (2026-02-02T21:20:38Z)
• 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)
• 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)
• VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model [38.61292051733335]
  We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework.<n>VarGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation.<n> Notably, VARGPT naturally supports capabilities in autoregressive visual generation and instruction-to-image synthesis, showcasing its versatility in both visual understanding and generation tasks.
  arXiv  Detail & Related papers  (2025-01-21T17:50:43Z)
• 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)
• 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)
• StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis [112.25071764647683]
  StrokeNUWA is a pioneering work exploring a better visual representation ''stroke tokens'' on vector graphics. equipped with stroke tokens, StrokeNUWA can significantly surpass traditional LLM-based and optimization-based methods. StrokeNUWA achieves up to a 94x speedup in inference over the speed of prior methods with an exceptional SVG code compression ratio of 6.9%.
  arXiv  Detail & Related papers  (2024-01-30T15:20:26Z)

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.