Saved in:
Bibliographic Details
Main Authors: Gkotsi, Polytimi Anna, Zadaianchuk, Andrii, Derakhshani, Mohammad Mahdi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.28995
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916070380535808
author Gkotsi, Polytimi Anna
Zadaianchuk, Andrii
Derakhshani, Mohammad Mahdi
author_facet Gkotsi, Polytimi Anna
Zadaianchuk, Andrii
Derakhshani, Mohammad Mahdi
contents Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end training or map features to compressed representations, discarding the dense spatial structure required for geometry-aware tasks like 3D asset generation. To address this, we propose GAP3D, a modular, diffusion-based approach that aligns VLM-generated latents directly to the complete, patch-level feature space of a pre-trained image encoder, enabling a frozen downstream generative model to utilize a VLM as prompt encoder while maintaining a spatially structured conditioning signal. Evaluated on 3D asset generation, our method bypasses the need for large-scale 3D data by training mainly on general-domain image-text pairs. It also exhibits emergent zero-shot capabilities for multimodal prompts, despite being trained exclusively on text input. Finally, while currently prioritizing high-level semantics over fine-grained detail, GAP3D demonstrates that the representation gap between VLM and image-encoder feature spaces can be partially bridged through diffusion-based alignment, taking the first steps towards a modular integration of foundation models through generative alignment to dense embedding spaces.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28995
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation
Gkotsi, Polytimi Anna
Zadaianchuk, Andrii
Derakhshani, Mohammad Mahdi
Computer Vision and Pattern Recognition
Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end training or map features to compressed representations, discarding the dense spatial structure required for geometry-aware tasks like 3D asset generation. To address this, we propose GAP3D, a modular, diffusion-based approach that aligns VLM-generated latents directly to the complete, patch-level feature space of a pre-trained image encoder, enabling a frozen downstream generative model to utilize a VLM as prompt encoder while maintaining a spatially structured conditioning signal. Evaluated on 3D asset generation, our method bypasses the need for large-scale 3D data by training mainly on general-domain image-text pairs. It also exhibits emergent zero-shot capabilities for multimodal prompts, despite being trained exclusively on text input. Finally, while currently prioritizing high-level semantics over fine-grained detail, GAP3D demonstrates that the representation gap between VLM and image-encoder feature spaces can be partially bridged through diffusion-based alignment, taking the first steps towards a modular integration of foundation models through generative alignment to dense embedding spaces.
title GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.28995