Dynamic Scene Novel View Synthesis via Deferred Spatio-temporal Consistency - Archive ouverte HAL Access content directly
Journal Articles Computers and Graphics Year : 2022

Dynamic Scene Novel View Synthesis via Deferred Spatio-temporal Consistency

Beatrix-Emőke Fülöp-Balogh
Julie Digne
Nicolas Bonneel


Structure from motion (SfM) enables us to reconstruct a scene via casual capture from cameras at different viewpoints, and novel view synthesis (NVS) allows us to render a captured scene from a new viewpoint. Both are hard with casual capture and dynamic scenes: SfM produces noisy and spatio-temporally sparse reconstructed point clouds, resulting in NVS with spatio-temporally inconsistent effects. We consider SfM and NVS parts together to ease the challenge. First, for SfM, we recover stable camera poses, then we defer the requirement for temporally-consistent points across the scene and reconstruct only a sparse point cloud per timestep that is noisy in space-time. Second, for NVS, we present a variational diffusion formulation on depths and colors that lets us robustly cope with the noise by enforcing spatio-temporal consistency via per-pixel reprojection weights derived from the input views. Together, this deferred approach generates novel views for dynamic scenes without requiring challenging spatio-temporally consistent reconstructions nor training complex models on large datasets. We demonstrate our algorithm on real-world dynamic scenes against classic and more recent learning-based baseline approaches.
Fichier principal
Vignette du fichier
2109.01018.pdf (28.91 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03374431 , version 1 (12-10-2021)



Beatrix-Emőke Fülöp-Balogh, Eleanor Tursman, James Tompkin, Julie Digne, Nicolas Bonneel. Dynamic Scene Novel View Synthesis via Deferred Spatio-temporal Consistency. Computers and Graphics, 2022, 107, pp.220. ⟨10.1016/j.cag.2022.07.019⟩. ⟨hal-03374431⟩
112 View
27 Download



Gmail Facebook X LinkedIn More