https://github.com/BillOuyang/3D-OGFlow
공식 코드Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds
ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
Just Go with the Flow: Self-Supervised Scene Flow Estimation
FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering
Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency
Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo
Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation
RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation
PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation
Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation
3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation
AANet: Adaptive Aggregation Network for Efficient Stereo Matching
SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Unsupervised Learning of 3D Scene Flow from Monocular Camera
DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds
DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model
SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow
3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling
SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving
Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.