Search Results for author:
Found 16 papers, 7 papers with code
Diff-Reg v1: Diffusion Matching Model for Registration Problem
Establishing reliable correspondences is essential for registration tasks such as 3D and 2D3D registration.
Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration
They typically compute candidate correspondences based on distances in the point feature space.
Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance
Robust obstacle avoidance is one of the critical steps for successful goal-driven indoor navigation tasks. Due to the obstacle missing in the visual image and the possible missed detection issue, visual image-based obstacle avoidance techniques still suffer from unsatisfactory robustness.
Robust Outlier Rejection for 3D Registration with Variational Bayes
Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.
Graph Matching Optimization Network for Point Cloud Registration
Point Cloud Registration is a fundamental and challenging problem in 3D computer vision.
Recurrent Structure Attention Guidance for Depth Super-Resolution
Second, instead of the coarse concatenation guidance, we propose a recurrent structure attention block, which iteratively utilizes the latest depth estimation and the image features to jointly select clear patterns and boundaries, aiming at providing refined guidance for accurate depth recovery.
Structure Flow-Guided Network for Real Depth Super-Resolution
Specifically, our framework consists of a cross-modality flow-guided upsampling network (CFUNet) and a flow-enhanced pyramid edge attention network (PEANet).
Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation
Our method decouples the translation from the entire transformation by predicting the object center and estimating the rotation in a center-aware manner.
Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking
The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization.
Generative Subgraph Contrast for Self-Supervised Graph Representation Learning
To this end, in this paper, we propose a novel adaptive subgraph generation based contrastive learning framework for efficient and robust self-supervised graph representation learning, and the optimal transport distance is utilized as the similarity metric between the subgraphs.
Unsupervised Visible-light Images Guided Cross-Spectrum Depth Estimation from Dual-Modality Cameras
Meanwhile, we release a large dual-spectrum depth estimation dataset with visible-light and far-infrared stereo images captured in different scenes to the society.
Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks
Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.
Reliable Inlier Evaluation for Unsupervised Point Cloud Registration
In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration.
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
Based on the reward function, for each state, we then construct a fused score function to evaluate the sampled transformations, where we weight the current and future rewards of the transformations.
Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration
By modeling the point cloud registration process as a Markov decision process (MDP), we develop a latent dynamic model of point clouds, consisting of a transformation network and evaluation network.
Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks
Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.
