SOURCE-LINKED INTELLIGENCE

Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

We address the problem of discovering repeated elements from a single image. In contrast to existing approaches that depend on large annotated datasets, curated multi-image collections, or object segmentation masks, we show that a single image can suffice to learn a meaningful object model in a completely bottom-up fashion, without any prior knowledge beyond a coarse scale prior. Our method learns a tunable image-space prototype of the repeated elements through a reconstruction objective, enabling the model to identify and synthesize consistent object instances within the same image. Experimen

Read original source ↗ Open in workspace

recordType

paper

region

Global