用稀疏摄像头实现高质量4D动态重建，突破传统密集阵列限制。
SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
- 提出时空畸变场统一建模生成观测的时空不一致性。
- 在多相机动态场景上实现高保真、时序一致的4D重建。
- 适用于稀疏、未标定摄像头，适合实际部署场景。
高质量4D重建可实现动态真实世界的逼真沉浸式渲染。然而，与静态场景仅需单个相机不同，高质量动态场景通常需要数十甚至上百个同步的密集相机阵列。这种对昂贵实验环境的依赖严重限制了其实际可扩展性。为此，我们提出一种基于稀疏摄像头的动态重建框架，利用大量但不一致的生成观测数据。核心创新是时空畸变场，该机制统一建模了生成观测在空间和时间维度上的不一致性。在此基础上，构建完整流程，实现从稀疏且未标定摄像头输入的4D重建。我们在多相机动态场景基准上评估该方法，实现了时空一致的高保真渲染，并显著优于现有方法。
原文摘要 · Abstract (English)
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. 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. Project page available at https://inspatio.github.io/sparse-cam4d/
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。