FLAT：用于几何精度场景生成的前馈隐式三角形斑点算法
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
摘要
从一张图像中生成可探索的3D场景，需要强大的生成先验以及适合后续使用的准确几何表示方式。当前的视频扩散模型能够生成高质量的图像，并且能在潜在空间中隐式地编码多视图几何结构。不过，现有的前馈潜在场景解码器通常输出的是具有模糊表面的体积型3D高斯分布，这限制了它们在模拟或标准图形处理中的应用。因此，我们希望能够将压缩后的视频扩散潜在特征直接转换为明确的表面元素，这样这些表面元素不仅易于渲染，而且更接近真实的几何形状。我们试图确定是否可以将压缩后的视频扩散潜在特征直接映射到明确的表面元素上。为此，我们引入了FLAT方法，并首次证明三角形碎片可以从视频扩散潜在特征中直接解码出来。与解码3D高斯分布相比，预测平面元素要困难得多，因为平面元素的方向对梯度流动有很大影响，往往会导致不良的梯度流动情况。FLAT方法通过两个关键机制解决了这个问题：一种以光线为中心的旋转参数化方法用于三角形回归，另一种新颖的产品窗口函数则有助于改善不同向三角形的渲染过程中的梯度流动。在标准的基准测试中，FLAT方法在保持良好视觉质量的同时，也取得了更高的几何精度。我们还发现，轻量级的测试时优化步骤可以将预测的三角形数据转换为完全不透明的、适合游戏引擎使用的格式，从而支持实时渲染。通过在相同的训练条件下评估3DGS、2DGS和三角形碎片变体，我们首次对前馈场景生成中的表示方式进行了系统分析。项目页面可在https://flat-splat.github.io查看。
English Abstract
Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric representations suitable for downstream use. Current video diffusion models offer high-quality generation and implicitly encode multi-view geometric structure in latent space. However, existing feedforward latent scene decoders typically output volumetric 3D Gaussians that lack a well-defined surface, limiting their use in simulation or standard graphics pipelines. This motivates decoding surface-aligned primitives that are not only renderable but also closer to explicit geometric assets. We ask whether compressed video diffusion latents can be mapped directly to explicit surface primitives in a single pass. To this end, we introduce FLAT and, for the first time, show that triangle splats can be decoded directly from video diffusion latents. Compared with decoding 3D Gaussians, predicting flat primitives is notoriously more challenging due to high sensitivity to primitive orientations, oftentimes leading to poor gradient flow. FLAT solves with two key ingredients: a ray-centered rotation parameterization for triangle regression and a novel product window function that improves gradient flow during differentiable triangle rendering. On standard benchmarks, FLAT achieves significantly better geometric accuracy while maintaining competitive visual quality compared to state-of-the-art feedforward baselines. We further show that a lightweight test-time refinement step converts the predicted triangle soup into a fully opaque, game-engine-ready representation that supports real-time rendering. By evaluating 3DGS, 2DGS, and triangle splatting variants under an identical training setup, we provide the first systematic analysis of representation tradeoffs in feedforward scene generation. The project page is available at https://flat-splat.github.io