利用重复元素提升3D场景重建质量，改善视角合成效果。
Splat and Replace: 3D Reconstruction with Repetitive Elements
- 通过分割与对齐重复物体，实现实例间信息共享。
- 在真实与合成场景中均显著提升视角合成质量。
- 特别适合有大量重复结构的室内或城市场景。
我们利用3D场景中的重复元素来改进新视角合成。尽管神经辐射场（NeRF）和3D高斯泼溅（3DGS）已大幅提高新视角合成质量，但当训练视图覆盖不全时，未见区域和被遮挡部分的渲染质量仍较差。我们的关键观察是，环境通常包含大量重复元素。为此，我们提出一种方法：对3DGS重建中的每个重复实例进行分割，将其配准对齐，并实现实例间的信息共享。该方法在提升几何精度的同时，也考虑了不同实例间的外观差异。我们在包含典型重复元素的多种合成与真实场景上进行了验证，显著提升了新视角合成的质量。
原文摘要 · Abstract (English)
We leverage repetitive elements in 3D scenes to improve novel view synthesis. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have greatly improved novel view synthesis but renderings of unseen and occluded parts remain low-quality if the training views are not exhaustive enough. Our key observation is that our environment is often full of repetitive elements. We propose to leverage those repetitions to improve the reconstruction of low-quality parts of the scene due to poor coverage and occlusions. We propose a method that segments each repeated instance in a 3DGS reconstruction, registers them together, and allows information to be shared among instances. Our method improves the geometry while also accounting for appearance variations across instances. We demonstrate our method on a variety of synthetic and real scenes with typical repetitive elements, leading to a substantial improvement in the quality of novel view synthesis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。