EGAS: Enhanced Geometry-aware 3D Asset Generation Using Gaussian Splatting

Current text-to-3D generation methods that rely solely on 2D diffusion supervision often suffer from incorrect geometry (e.g. geometric collapse) and unrealistic appearance (e.g. Janus issues) due to the inherent ambiguity in 2D lifting methods for scene representation optimization, which also leads to significant time consumption. In this paper, we introduce EGAS, a novel 3DG-based framework with enhanced geometry awareness, comprising geometry generation and texture refinement. Specifically, we extract pseudo-depth constraints and preliminary appearance guidance from coarse 3D priors to modulate the optimization direction and encourage consistent representation. Moreover, the reasonable geomtry formation is further secured through elaborately designed unsupervised constraints leveraging the particle property of 3D Gaussians. Extensive experiments demonstrate that our method achieves an excellent balance between efficiency and effectiveness, resulting in generated 3D assets with reasonable geometry, high fidelity appearance, and intricate details.