发表机构
College of Artificial Intelligence, Nanjing University of Posts and Telecommunications; College of Automation, Nanjing University of Posts and Telecommunications（南京邮电大学人工智能学院; 南京邮电大学自动化学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出DAV4框架，将RFM应用于4D高斯溅射参数实现动态4D场景重建，其F分数较基线提升0.044，在相关任务上优于现有模型且无需人工标注深度标签。
AI 中文摘要
我们提出Depth Anything V4（DAV4），这是一种用于从单目视频进行动态4D场景重建的框架。我们的核心贡献是将黎曼流匹配（RFM）应用于4D高斯溅射（4D Gaussian Splatting）参数，直接在非欧几里得流形（尺度、旋转、不透明度）上定义概率路径，确保所有中间状态均有效。通过受控实验，我们将RFM的贡献与测试时优化（TTO）和预训练分离开来：使用相同数据、架构和TTO的确定性MLP基线的F分数为0.762，而RFM达到0.806，+0.044的增益是RFM的独立贡献。我们提供修正后的计算成本分析：预训练为360 GPU小时，可在大规模部署（超过10,000个场景）中摊销。不确定性通过负高斯对数似然和预期校准误差进行量化。DAV4在动态重建和新视图合成方面优于先前的Depth Anything模型及逐场景4D-GS，且训练损失不使用人工标注的深度标签。
英文摘要
We present Depth Anything V4 (DAV4), a framework for dynamic 4D scene reconstruction from monocular video. Our key contribution is the application of Riemannian Flow Matching (RFM) to 4D Gaussian Splatting parameters, defining probability paths directly on non-Euclidean manifolds (scale, rotation, opacity), ensuring all intermediate states are valid. Through controlled experiments, we isolate RFM's contribution from test-time optimization (TTO) and pre-training. A deterministic MLP baseline with the same data, architecture, and TTO achieves F-score 0.762; RFM achieves 0.806 - the +0.044 gain is RFM's isolated contribution. We provide corrected computational cost analysis: pre-training is 360 GPU-hours, amortizing for large-scale deployment (over 10,000 scenes). Uncertainty is quantified via Negative Gaussian Log-Likelihood and Expected Calibration Error. DAV4 outperforms prior Depth Anything models and per-scene 4D-GS on dynamic reconstruction and novel-view synthesis, while using no human-annotated depth labels as training losses.
CommentsMajor errors in research
