用分钟级速度重建无标定视频的4D场景，适合快速泛化应用。
Instant4D: 4D Gaussian Splatting in Minutes
- 基于视觉SLAM与网格剪枝，实现高效几何恢复。
- 30倍提速训练，2分钟内完成建模，10分钟处理单段视频。
- 无需标定相机或深度传感器，适用于真实场景视频。
动态视图合成近年进展显著，但对未标定、随意拍摄的视频进行场景重建仍面临优化缓慢与参数估计复杂的问题。本文提出Instant4D，一种单目重建系统，利用原生4D表示，在数分钟内高效处理随意视频序列，无需相机标定或深度传感器。方法首先通过深度视觉SLAM实现几何恢复，再通过网格剪枝优化场景表示，显著减少冗余，模型体积压缩至原始10%以下。为高效处理时间动态，引入简化版4D高斯表示，实现30倍加速，训练时间缩短至两分钟内，且在多个基准测试中表现优异。单段视频可在10分钟内完成重建（如Dycheck数据集或典型200帧视频）。进一步应用于真实世界视频，验证其泛化能力。项目主页：https://instant4d.github.io/。
原文摘要 · Abstract (English)
Dynamic view synthesis has seen significant advances, yet reconstructing scenes from uncalibrated, casual video remains challenging due to slow optimization and complex parameter estimation. In this work, we present Instant4D, a monocular reconstruction system that leverages native 4D representation to efficiently process casual video sequences within minutes, without calibrated cameras or depth sensors. Our method begins with geometric recovery through deep visual SLAM, followed by grid pruning to optimize scene representation. Our design significantly reduces redundancy while maintaining geometric integrity, cutting model size to under 10% of its original footprint. To handle temporal dynamics efficiently, we introduce a streamlined 4D Gaussian representation, achieving a 30x speed-up and reducing training time to within two minutes, while maintaining competitive performance across several benchmarks. Our method reconstruct a single video within 10 minutes on the Dycheck dataset or for a typical 200-frame video. We further apply our model to in-the-wild videos, showcasing its generalizability. Our project website is published at https://instant4d.github.io/.
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。