PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views
For robotics and AR/VR applications requiring 3D reconstruction from sparse panoramas, PanoImager provides a robust alternative when traditional SfM/SLAM is ill-conditioned.
PanoImager addresses 3D reconstruction from sparse panoramic views under rotation-dominant, weak-parallax motion where SfM/SLAM fails. It achieves improved stability and cross-view consistency, enabling map refinement when initialization fails.
Panoramic sensing offers wide field-of-view coverage, yet 3D reconstruction from sparse panoramas remains challenging under rotation-dominant, weak-parallax motion. In such regimes, SfM/SLAM initialization is often ill-conditioned and unreliable. We present PanoImager, an SfM-free framework that combines feed-forward pose/depth priors, geometry-conditioned diffusion view completion, and depth-guided 3DGS optimization. Given only a few panoramic images, PanoImager decomposes them into local perspective views, synthesizes auxiliary observations to enrich sparse evidence, and stabilizes Gaussian optimization for improved cross-view consistency. Experiments on multiple benchmarks show improved stability under extreme sparsity, suggesting PanoImager as an offline/background component for map refinement when SfM/SLAM fails to initialize.