Copy-Trasform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914358238380032 |
|---|---|
| author | Gatenyo, Rotem Fried, Ohad |
| author_facet | Gatenyo, Rotem Fried, Ohad |
| contents | We study zero-shot 3D alignment of two given meshes, using a text prompt describing their spatial relation -- an essential capability for content creation and scene assembly. Earlier approaches primarily rely on geometric alignment procedures, while recent work leverages pretrained 2D diffusion models to model language-conditioned object-object spatial relationships. In contrast, we directly optimize the relative pose at test time, updating translation, rotation, and isotropic scale with CLIP-driven gradients via a differentiable renderer, without training a new model. Our framework augments language supervision with geometry-aware objectives: a variant of soft-Iterative Closest Point (ICP) term to encourage surface attachment and a penetration loss to discourage interpenetration. A phased schedule strengthens contact constraints over time, and camera control concentrates the optimization on the interaction region. To enable evaluation, we curate a benchmark containing diverse categories and relations, and compare against baselines. Our method outperforms all alternatives, yielding semantically faithful and physically plausible alignments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14207 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Copy-Trasform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints Gatenyo, Rotem Fried, Ohad Graphics Computer Vision and Pattern Recognition We study zero-shot 3D alignment of two given meshes, using a text prompt describing their spatial relation -- an essential capability for content creation and scene assembly. Earlier approaches primarily rely on geometric alignment procedures, while recent work leverages pretrained 2D diffusion models to model language-conditioned object-object spatial relationships. In contrast, we directly optimize the relative pose at test time, updating translation, rotation, and isotropic scale with CLIP-driven gradients via a differentiable renderer, without training a new model. Our framework augments language supervision with geometry-aware objectives: a variant of soft-Iterative Closest Point (ICP) term to encourage surface attachment and a penetration loss to discourage interpenetration. A phased schedule strengthens contact constraints over time, and camera control concentrates the optimization on the interaction region. To enable evaluation, we curate a benchmark containing diverse categories and relations, and compare against baselines. Our method outperforms all alternatives, yielding semantically faithful and physically plausible alignments. |
| title | Copy-Trasform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.14207 |