SparseCam4D：基于稀疏相机的时空一致 4D 重建
SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
用生成模型提供的多视角/多帧观测替代密集相机阵列，并通过时空畸变场统一建模生成观测在空间与时间上的不一致性，为稀疏、无标定输入下的动态 4D 重建提供了可复用的「生成观测去噪」思路。
原文依据 Our key innovation is the Spatio-Temporal Distortion Field, which provides a unified mechanism for modeling inconsistencies in generative observations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论高质量的 4D 重建能够实现动态真实世界的光照真实感与沉浸式渲染。然而，与仅用单台相机即可完整捕获的静态场景不同，高质量动态场景通常需要由数十甚至数百台同步相机组成的密集阵列。对这种昂贵实验室装置的依赖严重限制了实际可扩展性。为此，我们提出一种稀疏相机动态重建框架，利用丰富但不一致的生成观测。我们的核心创新是时空畸变场，它提供了一种统一机制，用于建模生成观测在空间与时间两个维度上的不一致性。在此基础上，我们构建了一套完整流程，能够从稀疏且未标定的相机输入实现 4D 重建。我们在多相机动态场景基准上评估了该方法，获得了时空一致的高保真渲染，并显著优于现有方法。
英文原文摘要 1086 字符
High-quality 4D reconstruction enables photorealistic and immersive rendering of the dynamic real world. However, unlike static scenes that can be fully captured with a single camera, high-quality dynamic scenes typically require dense arrays of tens or even hundreds of synchronized cameras. Dependence on such costly lab setups severely limits practical scalability. The reliance on such costly lab setups severely limits practical scalability. To this end, we propose a sparse-camera dynamic reconstruction framework that exploits abundant yet inconsistent generative observations. Our key innovation is the Spatio-Temporal Distortion Field, which provides a unified mechanism for modeling inconsistencies in generative observations across both spatial and temporal dimensions. Building on this, we develop a complete pipeline that enables 4D reconstruction from sparse and uncalibrated camera inputs. We evaluate our method on multi-camera dynamic scene benchmarks, achieving spatio-temporally consistent high-fidelity renderings and significantly outperforming existing approaches.