Depth Anything V4: Dynamic 4D Scene Reconstruction via Riemannian Flow Matching on 4D Gaussian Splatting

arXiv:2608.18388v1 Announce Type: new Abstract: 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.

Related

• DSD-GS: Dynamic-Static Decomposition of Gaussian Splatting for Efficient and High-Fidelity Dynamic Scene Reconstruction
• ERF-GS: Reconstructing Fast Motion from Disjoint Event-RGB Viewpoints
• Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes
• Stipple: Real-Time Incremental Gaussian Splatting with Visual-Inertial Tracking

Source: arXiv cs.CV | 2026-08-20