FTSplat: Feed-forward Triangle Splatting Network
This addresses the need for efficient, geometry-explicit 3D reconstruction in robotics and simulation, though it builds incrementally on existing feed-forward Gaussian splatting methods.
The paper tackles the problem of real-time 3D reconstruction for robotics and simulation by proposing a feed-forward framework that predicts continuous triangle surfaces from multi-view images, achieving simulation-ready models in a single forward pass without per-scene optimization.
High-fidelity three-dimensional (3D) reconstruction is essential for robotics and simulation. While Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) achieve impressive rendering quality, their reliance on time-consuming per-scene optimization limits real-time deployment. Emerging feed-forward Gaussian splatting methods improve efficiency but often lack explicit, manifold geometry required for direct simulation. To address these limitations, we propose a feed-forward framework for triangle primitive generation that directly predicts continuous triangle surfaces from calibrated multi-view images. Our method produces simulation-ready models in a single forward pass, obviating the need for per-scene optimization or post-processing. We introduce a pixel-aligned triangle generation module and incorporate relative 3D point cloud supervision to enhance geometric learning stability and consistency. Experiments demonstrate that our method achieves efficient reconstruction while maintaining seamless compatibility with standard graphics and robotic simulators.