Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912297684828160 |
|---|---|
| author | Bhattad, Anand Preechakul, Konpat Efros, Alexei A. |
| author_facet | Bhattad, Anand Preechakul, Konpat Efros, Alexei A. |
| contents | This paper proposes a novel scene understanding task called Visual Jenga. Drawing inspiration from the game Jenga, the proposed task involves progressively removing objects from a single image until only the background remains. Just as Jenga players must understand structural dependencies to maintain tower stability, our task reveals the intrinsic relationships between scene elements by systematically exploring which objects can be removed while preserving scene coherence in both physical and geometric sense. As a starting point for tackling the Visual Jenga task, we propose a simple, data-driven, training-free approach that is surprisingly effective on a range of real-world images. The principle behind our approach is to utilize the asymmetry in the pairwise relationships between objects within a scene and employ a large inpainting model to generate a set of counterfactuals to quantify the asymmetry. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21770 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting Bhattad, Anand Preechakul, Konpat Efros, Alexei A. Computer Vision and Pattern Recognition This paper proposes a novel scene understanding task called Visual Jenga. Drawing inspiration from the game Jenga, the proposed task involves progressively removing objects from a single image until only the background remains. Just as Jenga players must understand structural dependencies to maintain tower stability, our task reveals the intrinsic relationships between scene elements by systematically exploring which objects can be removed while preserving scene coherence in both physical and geometric sense. As a starting point for tackling the Visual Jenga task, we propose a simple, data-driven, training-free approach that is surprisingly effective on a range of real-world images. The principle behind our approach is to utilize the asymmetry in the pairwise relationships between objects within a scene and employ a large inpainting model to generate a set of counterfactuals to quantify the asymmetry. |
| title | Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21770 |