EgoFlow：梯度引导的流匹配用于第一人称6DoF物体运动生成
EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation
将流匹配与梯度引导推理结合，在生成 6DoF 轨迹时直接嵌入可微物理约束（碰撞避免、平滑性），无需后处理；其混合 Mamba-Transformer-Perceiver 架构对时序动态、场景几何与语义意图的联合建模方式，可迁移到其他需要物理合理性的轨迹生成或运动预测任务。
原文依据 gradient-guided inference process enforces differentiable physical constraints such as collision avoidance and motion smoothness
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从第一人称视频中理解和预测物体运动是具身感知与交互的基础。然而，由于遮挡、快速运动以及现有生成模型缺乏显式物理推理，生成物理一致的6DoF轨迹仍然具有挑战性。我们提出EgoFlow，一个流匹配框架，以多模态第一人称观测为条件合成逼真且物理合理的轨迹。EgoFlow采用混合Mamba-Transformer-Perceiver架构联合建模时序动态、场景几何和语义意图，同时梯度引导的推理过程强制执行可微物理约束，如碰撞避免和运动平滑性。这种组合无需后处理过滤或额外监督即可产生连贯且可控的运动生成。在HD-EPIC、EgoExo4D和HOT3D上的实验表明，EgoFlow在准确性、泛化和物理真实性方面优于基于扩散和Transformer的基线，碰撞率降低高达79%，并对未见场景具有强泛化能力。我们的结果凸显了基于流的生成建模在可扩展且物理基础的第一人称运动理解方面的前景。项目页面：https://abhi-rf.github.io/egoflow/
英文原文摘要 1304 字符
Understanding and predicting object motion from egocentric video is fundamental to embodied perception and interaction. However, generating physically consistent 6DoF trajectories remains challenging due to occlusions, fast motion, and the lack of explicit physical reasoning in existing generative models. We present EgoFlow, a flow-matching framework that synthesizes realistic and physically plausible trajectories conditioned on multimodal egocentric observations. EgoFlow employs a hybrid Mamba-Transformer-Perceiver architecture to jointly model temporal dynamics, scene geometry, and semantic intent, while a gradient-guided inference process enforces differentiable physical constraints such as collision avoidance and motion smoothness. This combination yields coherent and controllable motion generation without post-hoc filtering or additional supervision. Experiments on HD-EPIC, EgoExo4D, and HOT3D show that EgoFlow outperforms diffusion-based and transformer baselines in accuracy, generalization, and physical realism, reducing collision rates by up to 79%, and strong generalization to unseen scenes. Our results highlight the promise of flow-based generative modeling for scalable and physically grounded egocentric motion understanding. Project page: https://abhi-rf.github.io/egoflow/