AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Copy-Transform-Paste: Zero-Shot Object-Object Alignment Guided by Vision-Language and Geometric Constraints

Rotem Gatenyo, Ohad Fried

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CLIP text guidance (ablation)Copy-Transform-Paste · Object-object alignment benchmarkCLIP score: 0.3091 -> 0.3224Improved
add fractional soft-ICP attachment loss (ablation)Copy-Transform-Paste · Object-object alignment benchmarkText-Asset Alignment (GPT-4V): 969.40 -> 1028.72; intersection 0.0002 -> 0.0112Mixed
add penetration loss (ablation)Copy-Transform-Paste · Object-object alignment benchmarkIntersection volume: 0.0177 -> 0.0112Improved
add phased optimization with increasing weights (ablation)Copy-Transform-Paste · Object-object alignment benchmarkIntersection volume: 0.0141 -> 0.0112Improved
add camera scheduling (ablation)Copy-Transform-Paste · Object-object alignment benchmarkALIGN score: 14.5859 -> 14.9800Improved
use CLIP guidance instead of score distillation sampling (ablation)Copy-Transform-Paste · Object-object alignment benchmarkCLIP score: 0.3167 -> 0.3224Improved
use CLIP instead of SigLIP as guidance model (ablation)Copy-Transform-Paste · Object-object alignment benchmarkSigLIP score: SigLIP guidance 0.0387 vs 0.0380 SigLIP; CLIP 0.3145 vs 0.3224Mixed
also optimize isotropic scale (ablation)Copy-Transform-Paste · Object-object alignment benchmarkGPT-4V Overall: 1034.44 -> 1005.10Hurt
multi-start with CLIP selection for shrinkwrap baseline (ablation)Shrinkwrap · Object-object alignment benchmarkCLIP score: 0.3087 -> 0.3157Improved
use LLM to set penetration policy, initial scale and attachment ratioCopy-Transform-Paste · 61 held-out object pairsInitial scale MAE: 3.30 -> 0.46Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy