FTSplat: Feed-forward Triangle Splatting Network

TL;DR

FTSplat introduces a fast, feed-forward approach to generate 3D triangle meshes directly from multi-view images, enabling real-time high-fidelity reconstruction suitable for simulation without per-scene optimization.

Contribution

The paper presents a novel feed-forward framework for triangle primitive generation that predicts continuous surfaces from images, improving efficiency and geometric consistency over existing methods.

Findings

Achieves real-time 3D reconstruction without per-scene optimization

Produces simulation-ready models compatible with standard tools

Maintains high geometric fidelity and stability

Abstract

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.