AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance

Peiying Zhang, Nanxuan Zhao, Matthew Fisher, Yiran Xu, Jing Liao, Difan Liu

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add internal visual guidance (image tokens before SVG tokens) (ablation)DuetSVG · SVG-Hub-5M test (text-to-SVG)FID: 51.482 -> 33.574Improved
add internal visual guidance (ablation)DuetSVG · SVG-Hub-5M test (image-to-SVG)DINO: 0.939 -> 0.962Improved
add text-to-image pretraining stage (ablation)DuetSVG · SVG-Hub-5M test (text-to-SVG)FID: 36.953 -> 33.574Improved
add test-time scaling with image-guided SVG resampling (ablation)DuetSVG · SVG-Hub-5M test (text-to-SVG)FID: 35.066 -> 33.574Improved
add test-time scaling with image-guided SVG resampling (ablation)DuetSVG · SVG-Hub-5M test (image-to-SVG)LPIPS: 0.082 -> 0.075Improved
use image-guided SVG resampling instead of best-of-N (ablation)DuetSVG · SVG-Hub-5M test (text-to-SVG)sampling cost at given CLIP scoreImproved
fine-tune open-source VLM baselines on SVG-Hub-5MOmniSVG-3B · SVG-Hub-5M test (text-to-SVG)FID: 93.172 -> 58.237Improved
use DuetSVG with multimodal output vs fine-tuned Qwen3-VL-8B text-onlySVG generation backbone · SVG-Hub-5M test (text-to-SVG)FID: 43.720 -> 35.066Improved
use DuetSVG instead of VTracer for image-to-SVG reconstructionimage-to-SVG · SVG-Hub-5M test (image-to-SVG)DINO / LPIPS: DINO 0.968 -> 0.962; LPIPS 0.071 -> 0.075Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy