Compact Text-to-SDF via Latent Modeling

TL;DR — The paper introduces a compact Text-to-Shape model that efficiently generates 3D shapes by leveraging latent-code-based signed distance functions.

Abstract

This paper introduces CDiffSDF, a lightweight Text-to-Shape model designed for efficient 3D shape generation. By harnessing latent-code-based signed distance functions (SDFs), CDiffSDF not only produces high-resolution shapes but also features diffusion denoising capabilities within the latent space. Its generation ability is further boosted by integrating Gaussian noise during the SDF training phase, effectively counterbalancing the diffusion sampling perturbations. Transitioning from the core concept of Text-to-SDF, our model is versatile, as it can seamlessly adapt and generate shapes influenced by a range of inputs, including text, class, and image conditions. Experimental results demonstrate CDiffSDF's ability to produce detailed shapes, all within a compact design.