Papers
arxiv:2507.05499

LoomNet: Enhancing Multi-View Image Generation via Latent Space Weaving

Published on Jul 7
Authors:
,
,
,
,

Abstract

LoomNet, a multi-view diffusion architecture, generates consistent and high-quality multi-view images by leveraging a shared latent space and fusing viewpoint-specific encodings.

AI-generated summary

Generating consistent multi-view images from a single image remains challenging. Lack of spatial consistency often degrades 3D mesh quality in surface reconstruction. To address this, we propose LoomNet, a novel multi-view diffusion architecture that produces coherent images by applying the same diffusion model multiple times in parallel to collaboratively build and leverage a shared latent space for view consistency. Each viewpoint-specific inference generates an encoding representing its own hypothesis of the novel view from a given camera pose, which is projected onto three orthogonal planes. For each plane, encodings from all views are fused into a single aggregated plane. These aggregated planes are then processed to propagate information and interpolate missing regions, combining the hypotheses into a unified, coherent interpretation. The final latent space is then used to render consistent multi-view images. LoomNet generates 16 high-quality and coherent views in just 15 seconds. In our experiments, LoomNet outperforms state-of-the-art methods on both image quality and reconstruction metrics, also showing creativity by producing diverse, plausible novel views from the same input.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.05499 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.05499 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.05499 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.