Metraipolis › archive › dc_d38e36216701
Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis — arXiv:2609.07939
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07939
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:12:00.378Z
- SHA-256 of the archived text
318336c4ddc02cc96a61af773c494becb98c566d27b957d62a45708bffe4371c- Stable URL of this page
https://metraipolis.com/documento/dc_d38e36216701
How to cite
Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis — arXiv:2609.07939 — arXiv (en), https://arxiv.org/abs/2609.07939 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d38e36216701 (Metraipolis archive dc_d38e36216701, sha256 318336c4ddc02cc96a61af773c494becb98c566d27b957d62a45708bffe4371c)
BibTeX
@misc{dcd38e36216701,
title = {Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis — arXiv:2609.07939},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07939},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d38e36216701; sha256 318336c4ddc02cc96a61af773c494becb98c566d27b957d62a45708bffe4371c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07939. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Experiments on 116 real images from the FSC-147 dataset demonstrate that our method successfully learns coherent element models and captures intra-category variation on challenging images. Qualitative results reveal superior reconstructions and interpretable decompositions compared to classical decomposition, joint alignment, and 3D object modeling methods, while maintaining a simple 2D formulation. These results suggest that meaningful object discovery can emerge from single image learning alone. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.07939 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T14:49:57.260Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).