paper-with-me

Papers

GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis

2026-03-01 · Xuqin Wang, Tao Wu, Yanfeng Zhang, Lu Liu, Mingwei Sun, Yongliang Wang, Niclas Zeller, Daniel Cremers arxiv

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 advocate a Data-to-Data Flow Matching framework that learns deterministic transformations between paired views, enhancing view-consistent synthesis through explicit data coupling. Building on this, we propose Probability Density Geodesic Flow Matching (PDG-FM), which aligns interpolation trajectories with density-based geodesics of a data manifold. To enable tractable geodesic estimation, we employ a teacher-student framework that distills density-based geodesic interpolants into an efficient ambient-space predictor. Empirically, our method surpasses diffusion-based baselines on Objaverse and GSO30 datasets, 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.

📄 PDF Abstract BibTeX arXiv:2603.01010

Code (0)

등록된 구현이 없습니다.

Tasks

Novel View Synthesis

Similar Papers 제목 키워드 기반

The Geometry Behind Diffusion and Flow Matching: Gradient Flows and Geodesics in Wasserstein Space

2026-06-23 · Yian Yao, Weiwei Zhang arxiv

The space $\mathcal{P}_2(\mathbb{R}^d$) of probability measures with finite second moment carries a natural geometry: the quadratic Wasserstein distance W_2 makes it a complete metric space and, following Otto, a (formal…

Probability Density Geodesics in Image Diffusion Latent Space

2025-04-09 · CVPR 2025 1 · Qingtao Yu, Jaskirat Singh, Zhaoyuan Yang, Peter Henry Tu 외

Diffusion models indirectly estimate the probability density over a data space, which can be used to study its structure. In this work, we show that geodesics can be computed in diffusion latent space, where the norm ind…

Correcting Source Mismatch in Flow Matching with Radial-Angular Transport

2026-04-05 · Fouad Oubari, Mathilde Mougeot arxiv

Flow Matching is typically built from Gaussian sources and Euclidean probability paths. For heavy-tailed or anisotropic data, however, a Gaussian source induces a structural mismatch already at the level of the radial di…

Towards Variational Flow Matching on General Geometries

2025-02-18 · Olga Zaghen, Floor Eijkelboom, Alison Pouplin, Erik J. Bekkers

We introduce Riemannian Gaussian Variational Flow Matching (RG-VFM), an extension of Variational Flow Matching (VFM) that leverages Riemannian Gaussian distributions for generative modeling on structured manifolds. We de…

Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifolds

2024-06-27 · Masanari Kimura, Howard Bondell

The density ratio of two probability distributions is one of the fundamental tools in mathematical and computational statistics and machine learning, and it has a variety of known applications. Therefore, density ratio e…

Density Ratio Estimation