We tackle the problem of text-driven 3D generation from a geometry alignment perspective. Given a set of text prompts, we aim to generate a collection of objects with semantically corresponding parts aligned across them. Recent methods based on Score Distillation have succeeded in distilling the knowledge from 2D diffusion models to high-quality representations of the 3D objects. These methods handle multiple text queries separately, and therefore the resulting objects have a high variability in object pose and structure. However, in some applications, such as 3D asset design, it may be desirable to obtain a set of objects aligned with each other. In order to achieve the alignment of the corresponding parts of the generated objects, we propose to embed these objects into a common latent space and optimize the continuous transitions between these objects. We enforce two kinds of properties of these transitions: smoothness of the transition and plausibility of the intermediate objects along the transition. We demonstrate that both of these properties are essential for good alignment. We provide several practical scenarios that benefit from alignment between the objects, including 3D editing and object hybridization, and experimentally demonstrate the effectiveness of our method.this https URL
View on arXiv@article{ignatyev2025_2406.15020,
title={ A3D: Does Diffusion Dream about 3D Alignment? },
author={ Savva Ignatyev and Nina Konovalova and Daniil Selikhanovych and Oleg Voynov and Nikolay Patakin and Ilya Olkov and Dmitry Senushkin and Alexey Artemov and Anton Konushin and Alexander Filippov and Peter Wonka and Evgeny Burnaev },
journal={arXiv preprint arXiv:2406.15020},
year={ 2025 }
}