DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization
This addresses the problem of efficient, high-fidelity 3D reconstruction from fisheye cameras for VR/AR applications, offering an incremental improvement over existing 3DGS methods.
The paper tackles the problem of 3D scene reconstruction from fisheye camera images using 3D Gaussian Splatting (3DGS), which typically requires undistorting images first, causing information loss and artifacts. The result is DirectFisheye-GS, which integrates a fisheye camera model and cross-view joint optimization to enable native fisheye input, matching or surpassing state-of-the-art performance on public datasets.
3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering, greatly advancing VR/AR applications. Fisheye cameras, with their wider field of view (FOV), promise high-quality reconstructions from fewer inputs and have recently attracted much attention. However, since 3DGS relies on rasterization, most subsequent works involving fisheye camera inputs first undistort images before training, which introduces two problems: 1) Black borders at image edges cause information loss and negate the fisheye's large FOV advantage; 2) Undistortion's stretch-and-interpolate resampling spreads each pixel's value over a larger area, diluting detail density -- causes 3DGS overfitting these low-frequency zones, producing blur and floating artifacts. In this work, we integrate fisheye camera model into the original 3DGS framework, enabling native fisheye image input for training without preprocessing. Despite correct modeling, we observed that the reconstructed scenes still exhibit floaters at image edges: Distortion increases toward the periphery, and 3DGS's original per-iteration random-selecting-view optimization ignores the cross-view correlations of a Gaussian, leading to extreme shapes (e.g., oversized or elongated) that degrade reconstruction quality. To address this, we introduce a feature-overlap-driven cross-view joint optimization strategy that establishes consistent geometric and photometric constraints across views-a technique equally applicable to existing pinhole-camera-based pipelines. Our DirectFisheye-GS matches or surpasses state-of-the-art performance on public datasets.