GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functions

TL;DR

GeoGen is a novel SDF-based 3D generative model that produces high-fidelity, multi-view consistent 3D meshes from single-view collections, overcoming noise and detail limitations of previous neural radiance field methods.

Contribution

It introduces a learnable SDF representation with depth consistency constraints and adversarial training for improved 3D geometry synthesis.

Findings

GeoGen outperforms previous models in geometry quality.

It effectively generates detailed and consistent 3D meshes.

The synthetic human avatar dataset facilitates evaluation of 3D generative models.

Abstract

We introduce a new generative approach for synthesizing 3D geometry and images from single-view collections. Most existing approaches predict volumetric density to render multi-view consistent images. By employing volumetric rendering using neural radiance fields, they inherit a key limitation: the generated geometry is noisy and unconstrained, limiting the quality and utility of the output meshes. To address this issue, we propose GeoGen, a new SDF-based 3D generative model trained in an end-to-end manner. Initially, we reinterpret the volumetric density as a Signed Distance Function (SDF). This allows us to introduce useful priors to generate valid meshes. However, those priors prevent the generative model from learning details, limiting the applicability of the method to real-world scenarios. To alleviate that problem, we make the transformation learnable and constrain the rendered depth map to be consistent with the zero-level set of the SDF. Through the lens of adversarial training, we encourage the network to produce higher fidelity details on the output meshes. For evaluation, we introduce a synthetic dataset of human avatars captured from 360-degree camera angles, to overcome the challenges presented by real-world datasets, which often lack 3D consistency and do not cover all camera angles. Our experiments on multiple datasets show that GeoGen produces visually and quantitatively better geometry than the previous generative models based on neural radiance fields.