GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis
This work addresses view consistency in novel view synthesis, an incremental improvement for applications like 3D reconstruction and virtual reality.
The paper tackles the problem of inconsistent view predictions in novel view synthesis by proposing a deterministic Data-to-Data Flow Matching framework and Probability Density Geodesic Flow Matching, which improves structural coherence and smoother transitions compared to diffusion-based baselines.
Recent advances in generative modeling have substantially enhanced novel view synthesis, yet maintaining consistency across viewpoints remains challenging. Diffusion-based models rely on stochastic noise-to-data transitions, which obscure deterministic structures and yield inconsistent view predictions. We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views, enhancing view-consistent synthesis through explicit data coupling. To further enhance geometric coherence, we introduce Probability Density Geodesic Flow Matching (PDG-FM), which constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models. Such alignment with high-density regions of the data manifold promotes more realistic interpolants between samples. Empirically, our method surpasses diffusion-based NVS baselines, demonstrating improved structural coherence and smoother transitions across views. These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.