DisFlow: Scene Flow from Distance Field for Object Pose, Velocity Tracking, and Dynamic Object Reconstruction
2026-06-01 • Robotics
Robotics
AI summaryⓘ
The authors introduce DisFlow, a system that can track and understand moving objects in 3D space by using a special mathematical model called Gaussian Process Implicit Surfaces (GPIS). This model helps them figure out how objects change position and shape over time from distance measurements. Their method works directly in the object’s own coordinate system, making the tracking more consistent and accurate. DisFlow can do all this quickly while also building detailed 3D models of the objects as they move. The authors tested it on sequences of moving objects and showed it reliably tracks motion and reconstructs surfaces.
Scene flow6DoF pose estimationGaussian Process Implicit SurfacesSigned distance functionSurface normalsPoint cloud registrationProbabilistic fusionObject frameDynamic object trackingSurface reconstruction
Authors
Lan Wu, Sheila Sutjipto, Jennifer Wakulicz, Teresa Vidal-Calleja
Abstract
We present \emph{DisFlow}, a novel framework for online scene flow estimation from distance field that enables \emph{6DoF dynamic object pose estimation}, \emph{motion tracking}, and \emph{surface reconstruction}. The scene is represented by Gaussian Process Implicit Surfaces (GPIS), with surface normals serving as derivative constraints, enabling accurate signed distance computations near the surface and gradient queries with uncertainty. With this representation as a foundation, we compute a scene flow from the distance field that describes how surface points are transported over time in consecutive frames. Through our flow, we can estimate an object's pose and motion by incrementally registering a new observed point cloud via an elegant closed-form optimisation. Unlike prior methods that operate in the camera or world frame, our approach performs probabilistic fusion directly in the \emph{object frame}, where the object remains geometrically consistent over time. The tight coupling of the DisFlow method in space and time yields dense geometry, surface normals, object pose trajectories, velocities, and uncertainty, all at real-time rates. We evaluate DisFlow on dynamic object sequences and demonstrate that it achieves accurate pose and motion tracking while simultaneously reconstructing high-quality object surfaces. Code publicly available at \href{https://github.com/LanWu076/disflow_ros2}{https://github.com/LanWu076/disflow\_ros2}