EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation
This work addresses the problem of generating realistic and physically plausible object trajectories for embodied perception and interaction, representing a strong specific gain in the domain of egocentric motion understanding.
The paper tackled the problem of generating physically consistent 6DoF object motion from egocentric video, which is challenging due to occlusions and lack of explicit physical reasoning, and resulted in EgoFlow outperforming baselines by reducing collision rates by up to 79% and showing strong generalization to unseen scenes.
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 real-world datasets 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.