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.
KDMOS:Knowledge Distillation for Motion Segmentation
VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
Estimating Scene Flow in Robot Surroundings with Distributed Miniaturized Time-of-Flight Sensors
VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments
Toward Scalable, Flexible Scene Flow for Point Clouds
TARS: Traffic-Aware Radar Scene Flow Estimation
Floxels: Fast Unsupervised Voxel Based Scene Flow Estimation
HiMo: High-Speed Objects Motion Compensation in Point Clouds
MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation
SSF: Sparse Long-Range Scene Flow for Autonomous Driving
Zero-Shot Monocular Scene Flow Estimation in the Wild
STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation
BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events
FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation
Self-Supervised Scene Flow Estimation with Point-Voxel Fusion and Surface Representation
Neural Eulerian Scene Flow Fields
Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference
ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation
EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support
RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds
SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving
CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenario
Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering
SceneTracker: Long-term Scene Flow Estimation Network
Self-Supervised Multi-Frame Neural Scene Flow
Fast Kernel Scene Flow
DiffSF: Diffusion Models for Scene Flow Estimation
SeMoLi: What Moves Together Belongs Together
3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling
ICP-Flow: LiDAR Scene Flow Estimation with ICP
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.