用神经微分方程建模连续时空运动，实现无需标注的高质量场景流估计。
Neural Eulerian Scene Flow Fields
- 将场景流视为连续时空微分方程，用神经网络拟合运动场。
- 在真实数据上纯自监督训练，对鸟、网球等小物体仍保持高精度。
- 可直接跨域使用，适合自动驾驶与动态桌面场景的3D轨迹追踪。
我们将场景流重新定义为估计一个描述整个观测序列运动的连续时空常微分方程（ODE），并用神经先验表示。所提出的EulerFlow方法通过多个多视角重建目标优化该神经先验，在真实世界数据上实现纯自监督的高质量场景流估计。EulerFlow无需调参即可在大规模自动驾驶场景和动态桌面设置中直接使用。令人惊讶的是，它对小型快速移动物体（如鸟、网球）仍能生成高质量流估计，并通过长时间求解其预测的ODE展现出涌现的3D点跟踪能力。在Argoverse 2 2024场景流挑战赛中，EulerFlow超越所有现有方法，比次优无监督方法性能提升超2.5倍，甚至超过次优有监督方法10%以上。
原文摘要 · Abstract (English)
We reframe scene flow as the task of estimating a continuous space-time ODE that describes motion for an entire observation sequence, represented with a neural prior. Our method, EulerFlow, optimizes this neural prior estimate against several multi-observation reconstruction objectives, enabling high quality scene flow estimation via pure self-supervision on real-world data. EulerFlow works out-of-the-box without tuning across multiple domains, including large-scale autonomous driving scenes and dynamic tabletop settings. Remarkably, EulerFlow produces high quality flow estimates on small, fast moving objects like birds and tennis balls, and exhibits emergent 3D point tracking behavior by solving its estimated ODE over long-time horizons. On the Argoverse 2 2024 Scene Flow Challenge, EulerFlow outperforms all prior art, surpassing the next-best unsupervised method by more than 2.5x, and even exceeding the next-best supervised method by over 10%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。