Scene Flow Estimation
65 papers with code • 5 benchmarks • 8 datasets
Optical flow is a two-dimensional motion field in the image plane. It is the projection of the three-dimensional motion of the world. If the world is completely non-rigid, the motions of the points in the scene may all be indepen- dent of each other. One representation of the scene motion is therefore a dense three-dimensional vector field defined for every point on every surface in the scene. By analogy with optical flow, we refer to this three-dimensional motion field as scene flow.
Source: Vedula, Sundar, et al. "Three-dimensional scene flow." IEEE transactions on pattern analysis and machine intelligence 27.3 (2005): 475-480. pdf
Benchmarks
These leaderboards are used to track progress in Scene Flow Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
KITTI
FlyingThings3D
Argoverse 2
DeformingThings4D
Spring
Middlebury 2003
VBR
EKubric
Most implemented papers
FLOT: Scene Flow on Point Clouds Guided by Optimal Transport
Our main finding is that FLOT can perform as well as the best existing methods on synthetic and real-world datasets while requiring much less parameters and without using multiscale analysis.
Adversarial Self-Supervised Scene Flow Estimation
This work proposes a metric learning approach for self-supervised scene flow estimation.
FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation
yairkit/flowstep3d
•
•
CVPR 2021
Estimating the 3D motion of points in a scene, known as scene flow, is a core problem in computer vision.
Occlusion Guided Scene Flow Estimation on 3D Point Clouds
3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors.
RAFT-3D: Scene Flow using Rigid-Motion Embeddings
princeton-vl/RAFT-3D
•
•
CVPR 2021
We address the problem of scene flow: given a pair of stereo or RGB-D video frames, estimate pixelwise 3D motion.
PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds
weiyithu/PV-RAFT
•
•
CVPR 2021
In this paper, we propose a Point-Voxel Recurrent All-Pairs Field Transforms (PV-RAFT) method to estimate scene flow from point clouds.
Learning to Segment Rigid Motions from Two Frames
gengshan-y/rigidmask
•
•
CVPR 2021
Geometric motion segmentation algorithms, however, generalize to novel scenes, but have yet to achieve comparable performance to appearance-based ones, due to noisy motion estimations and degenerate motion configurations.
Weakly Supervised Learning of Rigid 3D Scene Flow
zgojcic/Rigid3DSceneFlow
•
•
CVPR 2021
We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies.
FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
InterDigitalInc/FESTA
•
•
CVPR 2021
Scene flow depicts the dynamics of a 3D scene, which is critical for various applications such as autonomous driving, robot navigation, AR/VR, etc.
Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds
Understanding the flow in 3D space of sparsely sampled points between two consecutive time frames is the core stone of modern geometric-driven systems such as VR/AR, Robotics, and Autonomous driving.
