Neural Eulerian Scene Flow Fields
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%.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingPoint TrackingScene Flow EstimationSimilar Papers 제목 키워드 기반
Animating Pictures with Eulerian Motion Fields
In this paper, we demonstrate a fully automatic method for converting a still image into a realistic animated looping video. We target scenes with continuous fluid motion, such as flowing water and billowing smoke. Our m…
Image-to-Image TranslationTranslationFrom Fixed Grids to Moving Particles:A Transferable Latent Operator for Fluid Dynamics
Lagrangian modeling is vital to fluid dynamics, as it characterizes particle transport and complements the Eulerian representation. However, Lagrangian trajectories are less commonly available than Eulerian fields, while…
MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field
We present MovingParts, a NeRF-based method for dynamic scene reconstruction and part discovery. We consider motion as an important cue for identifying parts, that all particles on the same part share the common motion p…
3D scene EditingNeRFPAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
Existing approaches to system identification (estimating the physical parameters of an object) from videos assume known object geometries. This precludes their applicability in a vast majority of scenes where object geom…
NeRFNeural RenderingObjectparameter estimation+13D Motion Magnification: Visualizing Subtle Motions with Time Varying Radiance Fields
Motion magnification helps us visualize subtle, imperceptible motion. However, prior methods only work for 2D videos captured with a fixed camera. We present a 3D motion magnification method that can magnify subtle motio…
Motion Magnification