CVMay 27

GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation

arXiv:2605.2899546.1h-index: 10
AI Analysis

For 3D asset generation, it offers a modular way to integrate VLMs with pre-trained generators, avoiding costly retraining, but the approach is incremental as it builds on existing diffusion and alignment techniques.

GAP3D aligns VLM latents to patch-level image encoder features via diffusion, enabling frozen 3D generators to use VLMs as prompt encoders without end-to-end training. It achieves zero-shot multimodal prompting and reduces reliance on 3D data, though it prioritizes semantics over fine details.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes