Scene Flow Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 5
- 보존된 평가 기록
- 22
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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
DeFlow: Decoder of Scene Flow Network in Autonomous Driving
FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units
DirDist: A Metric for Comparing 3D Shapes Using Directional Distance Fields
OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision
SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label
Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency
DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model
Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior
Multi-Body Neural Scene Flow
RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation
DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
Unleash the Potential of 3D Point Cloud Modeling with A Calibrated Local Geometry-driven Distance Metric
GMSF: Global Matching Scene Flow
ZeroFlow: Scalable Scene Flow via Distillation
Self-Supervised 3D Scene Flow Estimation Guided by Superpoints
Fast Neural Scene Flow
DEFLOW: Self-supervised 3D Motion Estimation of Debris Flow
Re-Evaluating LiDAR Scene Flow for Autonomous Driving
Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds
Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds
SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow
3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion
SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection
Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance
PointConvFormer: Revenge of the Point-based Convolution
What Matters for 3D Scene Flow Network
Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation
M-FUSE: Multi-frame Fusion for Scene Flow Estimation
Unsupervised Learning of 3D Scene Flow from Monocular Camera
RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds
UnPWC-SVDLO: Multi-SVD on PointPWC for Unsupervised Lidar Odometry
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.