YoNoSplat：前馈3D高斯泼溅只需一个模型
YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
AI总结：
YoNoSplat提出一个统一的前馈模型，可从任意数量、有无姿态和标定的图像中重建3D高斯泼溅，通过混合训练策略和相机距离归一化解决联合学习与尺度歧义问题，在标准基准上达到最先进性能且重建速度极快。
摘要：
从非结构化图像集合中快速灵活地进行3D场景重建仍然是一项重大挑战。我们提出了YoNoSplat，这是一个前馈模型，能够从任意数量的图像中重建高质量的3D高斯泼溅表示。我们的模型具有高度通用性，可有效处理有姿态和无姿态、已标定和未标定的输入。YoNoSplat为每个视图预测局部高斯和相机姿态，并使用预测的或提供的姿态将其聚合为全局表示。为克服联合学习3D高斯和相机参数的固有困难，我们引入了一种新颖的混合训练策略。该方法通过最初使用真值姿态聚合局部高斯，并逐步过渡到预测姿态与真值姿态的混合，来缓解两个任务之间的纠缠，从而避免训练不稳定和曝光偏差。我们进一步通过一种新颖的成对相机距离归一化方案以及将相机内参嵌入网络来解决尺度歧义问题。此外，YoNoSplat还预测内参，使其适用于未标定输入。YoNoSplat展现出卓越的效率，在NVIDIA GH200 GPU上仅用2.69秒即可从100个视图（分辨率为280x518）重建一个场景。它在无姿态和依赖姿态的标准基准测试中均达到了最先进的性能。我们的项目页面位于https://botaoye.github.io/yonosplat/。
英文摘要：
Fast and flexible 3D scene reconstruction from unstructured image collections remains a significant challenge. We present YoNoSplat, a feedforward model that reconstructs high-quality 3D Gaussian Splatting representations from an arbitrary number of images. Our model is highly versatile, operating effectively with both posed and unposed, calibrated and uncalibrated inputs. YoNoSplat predicts local Gaussians and camera poses for each view, which are aggregated into a global representation using either predicted or provided poses. To overcome the inherent difficulty of jointly learning 3D Gaussians and camera parameters, we introduce a novel mixing training strategy. This approach mitigates the entanglement between the two tasks by initially using ground-truth poses to aggregate local Gaussians and gradually transitioning to a mix of predicted and ground-truth poses, which prevents both training instability and exposure bias. We further resolve the scale ambiguity problem by a novel pairwise camera-distance normalization scheme and by embedding camera intrinsics into the network. Moreover, YoNoSplat also predicts intrinsic parameters, making it feasible for uncalibrated inputs. YoNoSplat demonstrates exceptional efficiency, reconstructing a scene from 100 views (at 280x518 resolution) in just 2.69 seconds on an NVIDIA GH200 GPU. It achieves state-of-the-art performance on standard benchmarks in both pose-free and pose-dependent settings. Our project page is at https://botaoye.github.io/yonosplat/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
