3DGS-Enhancer：利用视图一致的2D扩散先验增强无界3D高斯飞溅

3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors

October 21, 2024

作者: Xi Liu, Chaoyi Zhou, Siyu Huang

cs.AI

摘要

新视角合成旨在从多个输入图像或视频中生成场景的新视角，最近的技术进展如3D高斯飘粒（3DGS）在生成逼真渲染方面取得了显著成功，并具有高效的流程。然而，在具有挑战性的设置下生成高质量的新视角，例如稀疏输入视角，由于欠采样区域信息不足，通常会导致明显的伪影，仍然具有一定难度。本文提出了3DGS-Enhancer，这是一个用于提升3DGS表示质量的新型流程。我们利用2D视频扩散先验来解决具有挑战性的3D视角一致性问题，重新构建为在视频生成过程中实现时间一致性。3DGS-Enhancer恢复了渲染的新视角的视角一致潜在特征，并通过空间-时间解码器将其与输入视角整合。增强的视角然后用于微调初始3DGS模型，显著提高了其渲染性能。对无界场景的大规模数据集进行的大量实验表明，与最先进方法相比，3DGS-Enhancer在重建性能和高保真渲染结果方面表现出色。项目网页为https://xiliu8006.github.io/3DGS-Enhancer-project。

English

Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable success in producing photorealistic renderings with efficient pipelines. However, generating high-quality novel views under challenging settings, such as sparse input views, remains difficult due to insufficient information in under-sampled areas, often resulting in noticeable artifacts. This paper presents 3DGS-Enhancer, a novel pipeline for enhancing the representation quality of 3DGS representations. We leverage 2D video diffusion priors to address the challenging 3D view consistency problem, reformulating it as achieving temporal consistency within a video generation process. 3DGS-Enhancer restores view-consistent latent features of rendered novel views and integrates them with the input views through a spatial-temporal decoder. The enhanced views are then used to fine-tune the initial 3DGS model, significantly improving its rendering performance. Extensive experiments on large-scale datasets of unbounded scenes demonstrate that 3DGS-Enhancer yields superior reconstruction performance and high-fidelity rendering results compared to state-of-the-art methods. The project webpage is https://xiliu8006.github.io/3DGS-Enhancer-project .