DualReg: Dual-Space Filtering and Reinforcement for Rigid Registration
Noisy, partially overlapping data and the need for real-time processing pose major challenges for rigid registration. Considering that feature-based matching can handle large transformation differences but suffers from limited accuracy, while local geometry-based matching can achieve fine-grained local alignment but relies heavily on a good initial transformation, we propose a novel dual-space paradigm to fully leverage the strengths of both approaches. First, we introduce an efficient filtering mechanism consisting of a computationally lightweight one-point RANSAC algorithm and a subsequent refinement module to eliminate unreliable feature-based correspondences. Subsequently, we treat the filtered correspondences as anchor points, extract geometric proxies, and formulate an effective objective function with a tailored solver to estimate the transformation. Experiments verify our method's effectiveness, as demonstrated by a 32x CPU-time speedup over MAC on KITTI with comparable accuracy. Project page: https://ustc3dv.github.io/DualReg/.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
MoDA: Modeling Deformable 3D Objects from Casual Videos
In this paper, we focus on the challenges of modeling deformable 3D objects from casual videos. With the popularity of neural radiance fields (NeRF), many works extend it to dynamic scenes with a canonical NeRF and a def…
NeRFDual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling
Objects' rigid motions in 3D space are described by rotations and translations of a highly-correlated set of points, each with associated $x,y,z$ coordinates that real-valued networks consider as separate entities, losin…
Human Pose ForecastingMeMoSORT: Memory-Assisted Filtering and Motion-Adaptive Association Metric for Multi-Person Tracking
Multi-object tracking (MOT) in human-dominant scenarios, which involves continuously tracking multiple people within video sequences, remains a significant challenge in computer vision due to targets' complex motion and …
Multi-Object TrackingLoRe: Personalizing LLMs via Low-Rank Reward Modeling
Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches ofte…
Dynamics on Lie groups with applications to attitude estimation
The problem of filtering - propagation of states through stochastic differential equations (SDEs) and association of measurement data using Bayesian inference - in a state space which forms a Lie group is considered. Par…
Bayesian Inference