GaussianWorld：面向流式3D占据预测的高斯世界模型
GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction
AI总结：
针对自动驾驶3D占据预测现有方法未利用场景演化先验的问题，提出基于GaussianWorld的框架，将任务重构为4D占据预测，分解场景演化三因素并在3D高斯空间推理，在nuScenes数据集上以零额外计算实现mIoU超2%的提升。
摘要：
3D占据预测因能对周围环境进行全面感知，在自动驾驶领域具有重要意义。为融合时序输入，现有大多数方法通过融合过往帧的表征来推断当前3D占据状态，但这类方法未考虑驾驶场景的连续性，忽略了3D场景演化所提供的强先验（例如只有动态物体才会运动）。本文提出一种基于世界模型的框架，利用场景演化信息辅助感知。我们将3D占据预测重新建模为以当前传感器输入为条件的4D占据预测问题，将场景演化分解为三个因素：1）静态场景的自车运动对齐；2）动态物体的局部运动；3）新观测场景的补全。随后我们采用高斯世界模型（GaussianWorld）显式利用这些先验，结合当前RGB观测在3D高斯空间中推断场景演化。我们在广泛使用的nuScenes数据集上评估了该框架的有效性，GaussianWorld在未引入额外计算量的情况下，相较单帧基线模型的mIoU提升超过2%。代码位于：https://github.com/zuosc19/GaussianWorld。
英文摘要：
3D occupancy prediction is important for autonomous driving due to its comprehensive perception of the surroundings. To incorporate sequential inputs, most existing methods fuse representations from previous frames to infer the current 3D occupancy. However, they fail to consider the continuity of driving scenarios and ignore the strong prior provided by the evolution of 3D scenes (e.g., only dynamic objects move). In this paper, we propose a world-model-based framework to exploit the scene evolution for perception. We reformulate 3D occupancy prediction as a 4D occupancy forecasting problem conditioned on the current sensor input. We decompose the scene evolution into three factors: 1) ego motion alignment of static scenes; 2) local movements of dynamic objects; and 3) completion of newly-observed scenes. We then employ a Gaussian world model (GaussianWorld) to explicitly exploit these priors and infer the scene evolution in the 3D Gaussian space considering the current RGB observation. We evaluate the effectiveness of our framework on the widely used nuScenes dataset. Our GaussianWorld improves the performance of the single-frame counterpart by over 2% in mIoU without introducing additional computations. Code: https://github.com/zuosc19/GaussianWorld.
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。
