Papers with Code 아카이브
3D Point Cloud Interpolation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 9
Point cloud interpolation is a fundamental problem for 3D computer vision. Given a low temporal resolution (frame rate) point cloud sequence, the target of interpolation is to generate a smooth point cloud sequence with high temporal resolution (frame rate).
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
FastMAC: Stochastic Spectral Sampling of Correspondence Graph
PSS-BA: LiDAR Bundle Adjustment with Progressive Spatial Smoothing
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
PCR-99: A Practical Method for Point Cloud Registration with 99 Percent Outliers
CLIPPER+: A Fast Maximal Clique Algorithm for Robust Global Registration
CLIPPER: Robust Data Association without an Initial Guess
Registration of algebraic varieties using Riemannian optimization
Iterative Feedback Network for Unsupervised Point Cloud Registration
PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations
OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision
Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration
On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods
D3Former: Jointly Learning Repeatable Dense Detectors and Feature-enhanced Descriptors via Saliency-guided Transformer
SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration
PCRDiffusion: Diffusion Probabilistic Models for Point Cloud Registration
DIPR: Efficient Point Cloud Registration via Dynamic Iteration
ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models
Adaptive Multi-step Refinement Network for Robust Point Cloud Registration
E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning
Nothing Stands Still: A Spatiotemporal Benchmark on 3D Point Cloud Registration Under Large Geometric and Temporal Change
Cross-Modal Information-Guided Network using Contrastive Learning for Point Cloud Registration
Transformation Decoupling Strategy based on Screw Theory for Deterministic Point Cloud Registration with Gravity Prior
HDMNet: A Hierarchical Matching Network with Double Attention for Large-scale Outdoor LiDAR Point Cloud Registration
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
DBDNet:Partial-to-Partial Point Cloud Registration with Dual Branches Decoupling
OAAFormer: Robust and Efficient Point Cloud Registration Through Overlapping-Aware Attention in Transformer
Colmap-PCD: An Open-source Tool for Fine Image-to-point cloud Registration
Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
KDD-LOAM: Jointly Learned Keypoint Detector and Descriptors Assisted LiDAR Odometry and Mapping
Partial Transport for Point-Cloud Registration
Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature
CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registration
AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration
FF-LOGO: Cross-Modality Point Cloud Registration with Feature Filtering and Local to Global Optimization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.