SketchRevive：扩散先验引导多模态大语言模型的细粒度像素到矢量草图补全
SketchRevive: Fine-Grained Pixel-to-Vector Sketch Completion with Diffusion-Prior-Guided Multimodal LLMs
把扩散模型的多尺度 UNet 特征与线条预测 logits 注入 MLLM 视觉嵌入并做词元压缩，这一「扩散先验聚合编码」思路可迁移到任何需要把像素级生成先验喂给多模态大模型的图像编辑/矢量化任务。
原文依据 injecting multi-scale UNet features from Stage I into the MLLM's visual embeddings and using line prediction logits for token compression
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论将来自多种媒介的稀疏、残缺像素草图转化为完整、可编辑的矢量图，在数字创作中至关重要却研究不足。已有方法要么从零生成，要么只修补局部缺口而不预测全局结构，导致轮廓粗糙、细节有限。为此，我们提出 SketchRevive，一个两阶段的细粒度像素到矢量草图补全框架，将基于扩散的像素补全与 MLLM 驱动的细化及矢量化相结合，产出连贯且细节忠实的 SVG 结果。具体而言，我们首先通过增强来自纸张与白板的带笔画标注草图，构建了一个实用基准。第一阶段训练一个带有线条分布检测头的扩散模型来预测逐像素的笔画存在性，生成结构与视觉上一致的补全结果。第二阶段微调一个 MLLM 以进行结构感知的 SVG 矢量化并迭代细化，以实例级笔画属性相似度进行优化。为对齐两个阶段的关键线索（如空间结构、外观细节），我们引入扩散先验聚合编码模块，将第一阶段的多尺度 UNet 特征注入 MLLM 的视觉嵌入，并利用线条预测 logits 进行词元压缩，以优先保留信息量大的词元。实验表明，SketchRevive 能补全出拓扑连贯的矢量输出，具有高保真度与可识别性，同时保留用户意图，适用于交互式创作与艺术设计。
英文原文摘要 1521 字符
Transforming sparse, partial pixel sketches from diverse media into complete, editable vector drawings is essential yet underexplored in digital creation. Prior methods either generate from scratch or inpaint local gaps without predicting global structure, leading to coarse contours and limited detail. To address this, we introduce SketchRevive, a two-stage framework for fine-grained pixel-to-vector sketch completion that couples diffusion-based pixel completion with MLLM-driven refinement and vectorization to produce coherent, detail-faithful SVG results. Specifically, we first construct a practical benchmark by augmenting stroke-annotated sketches from paper and whiteboards. Stage I trains a diffusion model with a line-distribution head to predict per-pixel stroke presence, producing structurally and visually consistent completions. Stage II fine-tunes an MLLM for structure-aware SVG vectorization with iterative refinement, optimized by instance-level stroke attribute similarities. To align key clues, e.g., spatial structure, appearance details across both stages, we introduce a diffusion-prior aggregated encoding module by injecting multi-scale UNet features from Stage I into the MLLM's visual embeddings and using line prediction logits for token compression to prioritize informative tokens. Experiments indicate that SketchRevive completes topology-coherent vector outputs with high fidelity and recognizability while preserving user intent, suitable for interactive creation and artistic design.