UFO：统一前馈与优化方法的大规模驾驶场景建模
UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling
把前馈重建与逐场景优化统一成循环式 4D 场景 token 表示，并用可见性过滤把 3D 到像素对应的复杂度从二次降到近线性，可直接迁移到长序列动态场景重建与新视角合成。
原文依据 A visibility-based filtering mechanism exploits the locality of 3D-to-pixel correspondence, reducing complexity from quadratic to near-linear in sequence length.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论动态驾驶场景建模对自动驾驶仿真与闭环学习至关重要。近期前馈方法借助数据驱动的先验实现了快速推理，但由于序列长度上的二次复杂度以及对动态物体的限制性假设，它们在长距离驾驶序列上表现不佳。我们提出 UFO，一种新的循环式范式，结合了基于优化的方法与前馈方法的优势，实现高效的长距离 4D 建模。我们的方法维护一个由场景 token 组成的持久 4D 场景表示，随着新帧到来逐步细化，使未来的观测能够修正早先不确定的预测。一种基于可见性的过滤机制利用 3D 到像素对应的局部性，将复杂度从序列长度上的二次降低到近线性。对于动态物体，我们引入带可学习生命周期的物体位姿引导建模，无需运动学假设即可实现复杂的长距离运动。在 Waymo 开放数据集上的实验表明，UFO 在 2 秒、8 秒以及零样本 16 秒序列上均显著优于逐场景优化与前馈基线。
英文原文摘要 1192 字符
Dynamic driving scene modeling is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods offer fast inference through data-driven priors, they struggle with long-range driving sequences due to quadratic complexity in sequence length and restrictive assumptions for dynamic objects. We propose UFO, a novel recurrent paradigm that combines the strengths of optimization-based and feed-forward methods for efficient long-range 4D modeling. Our approach maintains a persistent 4D scene representation composed of scene tokens that are progressively refined as new frames arrive, enabling future observations to correct earlier uncertain predictions. A visibility-based filtering mechanism exploits the locality of 3D-to-pixel correspondence, reducing complexity from quadratic to near-linear in sequence length. For dynamic objects, we introduce object pose-guided modeling with learned lifespans, enabling complex long-range motion without kinematic assumptions. Experiments on the Waymo Open Dataset demonstrate that UFO significantly outperforms both per-scene optimization and feed-forward baselines across 2s, 8s, and zero-shot 16s sequences.