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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/leolyj/dca-srsfe
공식 코드https://github.com/lilac-lee/fastkernelsf
공식 코드https://github.com/lilac-lee/fastnsf
공식 코드https://github.com/lilac-lee/neural_scene_flow_prior
공식 코드https://github.com/lmb-freiburg/sf2se3
공식 코드SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection
https://github.com/mcg-nju/camliflow
공식 코드CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation
https://github.com/princeton-vl/RAFT-3D
공식 코드https://github.com/prs-eth/DeFlow
공식 코드https://github.com/rsy6318/clgd
공식 코드https://github.com/scnu-rislab/kdmos
공식 코드https://github.com/scnu-rislab/mambaflow
공식 코드MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation
https://github.com/supersyq/spflownet
공식 코드Self-Supervised 3D Scene Flow Estimation Guided by Superpoints
https://github.com/toytiny/cmflow
공식 코드Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
https://github.com/toytiny/milliflow
공식 코드milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
https://github.com/toytiny/raflow
공식 코드Self-Supervised Scene Flow Estimation with 4-D Automotive Radar
https://github.com/tudelft-iv/voteflow
공식 코드VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow
https://github.com/twhui/LiteFlowNet3
공식 코드LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
https://github.com/uncbiag/shapmagn
공식 코드Accurate Point Cloud Registration with Robust Optimal Transport
https://github.com/vacany/let-it-flow
공식 코드Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering
https://github.com/valeoai/FLOT
공식 코드FLOT: Scene Flow on Point Clouds Guided by Optimal Transport
https://github.com/visinf/multi-mono-sf
공식 코드https://github.com/visinf/self-mono-sf
공식 코드https://github.com/weiyithu/PV-RAFT
공식 코드PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds
https://github.com/wwh0411/fedrsu
공식 코드FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units
https://github.com/wwsource/scenetracker
공식 코드https://github.com/xingyul/meteornet
공식 코드MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences
https://github.com/yairkit/flowstep3d
공식 코드FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation
https://github.com/yanconglin/icp-flow
공식 코드https://github.com/zgojcic/Rigid3DSceneFlow
공식 코드https://github.com/zhangyushan3/diffsf
공식 코드https://github.com/zhangyushan3/gmsf
공식 코드https://github.com/FilippoAleotti/Dwarf-Tensorflow
https://github.com/HKBU-HPML/FADNet
https://github.com/HKBU-HPML/IRS
https://github.com/arashk7/DispNet_Keras
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.