CGGS：一致性增强的几何高斯泼溅用于第一人称3D场景生成

摘要

在自中心三维场景生成中，由于视点重叠有限且个体视角对场景解读影响显著，仍面临诸多挑战。这些因素阻碍了视点一致且语义对齐的视觉内容的生成，以及精确几何结构的构建。本文提出CGGS——一种文本到三维框架，旨在增强三维内容感知能力并解决自中心场景生成中的几何畸变问题。首先，提出自中心生成器（Ego-centric Generator），通过微调多视角潜在扩散模型并引入一致性增强损失，生成与文本描述对齐的一致性高保真二维内容。接着，布局装饰器（Layout Decorator）利用光流与点轨迹对应关系估计深度，从而从自中心二维先验中生成稠密点云作为粗略布局。在此初始化的基础上，提出几何精炼器（Geometric Refiner），通过基于熵的互信息深度损失（MID）结合层次化优化方案，增强三维高斯重建效果，提升视觉质量与几何结构。大量实验表明，CGGS在生成连贯且准确的文本驱动三维场景方面优于先前方法。项目页面：https://cggs-26.github.io/cggs26/。

English

Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation. These factors hinder the creation of viewpoint-consistent and semantically aligned visual content, as well as the construction of accurate geometric structures. In this paper, we propose CGGS, a text-to-3D framework aiming to enhance 3D-content-awareness and address geometric distortions in ego-centric scene generation. Firstly, the Ego-centric Generator is proposed by fine-tuning a Multi-View Latent Diffusion Model with consistency-augmented loss to generate consistent, high-fidelity 2D content aligned with textual descriptions. Then, Layout Decorator leverages optical flow and point-track correspondence to estimate depth, therefore producing dense point clouds as coarse layouts from the ego-centric 2D priors. Building on this initialization, Geometric Refiner is proposed to enhance 3D Gaussian reconstruction via an entropy-based Mutual Information Depth Loss (MID) combined with a hierarchical optimization scheme for improving visual quality and geometric structure. Comprehensive experiments demonstrate that softred{CGGS} outperforms previous methods in generating coherent and accurate text-driven 3D scenes. Project page: https://cggs-26.github.io/cggs26/.