SOTAVerified

Scene Flow Estimation

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

Papers

Showing 110 of 152 papers

TitleStatusHype
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second0
KDMOS:Knowledge Distillation for Motion SegmentationCode0
VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction0
Estimating Scene Flow in Robot Surroundings with Distributed Miniaturized Time-of-Flight Sensors0
VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene FlowCode1
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction0
Toward Scalable, Flexible Scene Flow for Point Clouds0
SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments0
TARS: Traffic-Aware Radar Scene Flow Estimation0
Floxels: Fast Unsupervised Voxel Based Scene Flow Estimation0
Show:102550
← PrevPage 1 of 16Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FastNSFEPE 3-Way0.11Unverified
2FastFlow3DEPE 3-Way0.06Unverified
3NSFPEPE 3-Way0.06Unverified
4ZeroFlow 5x XLEPE 3-Way0.05Unverified
5SeFlowEPE 3-Way0.05Unverified
6TrackFlowEPE 3-Way0.05Unverified
7DeFlowEPE 3-Way0.03Unverified