CoGSD: Fast Consistency Generation Based on 3D Gaussian Splatting

Authors: Zhenghui Sun Xianglong Li Shuyuan Chang
Conference: ICIC 2024 Posters, Tianjin, China, August 5-8, 2024
Pages: 245-258
Keywords: 3D Model Generation, Multi-view Consistent Image Generation, 3D Gaussian Splatting, Score Distillation Sampling, Diffusion Model

Abstract

This research introduces a multi-view consistent 3D modeling method CoGSD Cosistent Gaussian Splatting Dreamer , this is construct 3D models rapidly with multi-view consistency through 3D Gaussian Splatting. 3D Gaussian Splatting generation fails to construct effective 3D assets due to the lack of stable ground truth. In addition, the expansion characteristics of 3D Gaussian Splatting itself lead to abnormal expansion of saturated Gaussian points and multi-view inconsistency problems. At the same time, the lack of credible ground truth will also lead to multi-view inconsistency problems. To solve this problem, we use a pre-trained consistent diffusion model to generate consistent viewpoints. In our framework, instead of generating diffusion with a single a priori perspective, the 2D image generation method of SDS uses a controlnet-tuned pre-trained model to generate 2D images with coherent viewpoints, resulting in high-quality 3D model generation. The method in this paper provides an effective solution for 3D modeling and is expected to be widely used in the field of 3D modeling and visual effects.
📄 View Full Paper (PDF) 📋 Show Citation