Abstract
Semantic Scene Completion (SSC) aims to infer complete 3D geometry and semantics from monocular images, serving as a crucial capability for camera-based perception in autonomous driving. However, existing SSC methods relying on temporal stacking or depth projection often lack explicit motion reasoning and struggle with occlusions and noisy depth supervision. We propose CurriFlow, a novel semantic occupancy prediction framework that integrates optical flow-based temporal alignment with curriculum-guided depth fusion. CurriFlow employs a multi-level fusion strategy to align segmentation, visual, and depth features across frames using pre-trained optical flow, thereby improving temporal consistency and dynamic object understanding. To enhance geometric robustness, a curriculum learning mechanism progressively transitions from sparse yet accurate LiDAR depth to dense but noisy stereo depth during training, ensuring stable optimization and seamless adaptation to real-world deployment. Furthermore, semantic priors from the Segment Anything Model (SAM) provide category-agnostic supervision, strengthening voxel-level semantic learning and spatial consistency. Experiments on the SemanticKITTI benchmark demonstrate that CurriFlow achieves state-of-the-art performance with a mean IoU of 16.9, validating the effectiveness of our motion-guided and curriculum-aware design for camera-based 3D semantic scene completion.
Abstract (translated)
语义场景补全（SSC）旨在从单目图像中推断出完整的三维几何和语义信息，这对于基于摄像头的自动驾驶感知能力至关重要。然而，现有的SSC方法依赖于时间堆叠或深度投影时往往缺乏显式的运动推理，并且在处理遮挡以及噪声深度监督方面存在困难。我们提出了一种新颖的语义占用预测框架CurriFlow，该框架结合了基于光学流的时间对齐与引导式课程学习的深度融合。 CurriFlow采用多级融合策略，利用预训练的光学流，在帧间对齐分割、视觉和深度特征，从而提高时间一致性并增强动态对象的理解。为了提升几何鲁棒性，引入了一种课程学习机制，在训练过程中逐步从稀疏但准确的激光雷达深度过渡到密集却带有噪声的立体深度，确保了稳定的优化及在实际部署中的平滑适应。 此外，来自Segment Anything Model（SAM）的语义先验提供了类别无关的监督信息，加强了体素级语义学习和空间一致性。在SemanticKITTI基准测试上的实验表明，CurriFlow达到了最先进的性能表现，平均IoU为16.9%，验证了我们基于运动引导及课程感知的设计对于基于摄像头的三维语义场景补全的有效性。
URL
https://arxiv.org/abs/2510.12362
