专题:Advanced Vision and Imaging

This cluster of papers focuses on various aspects of stereo vision, depth estimation, optical flow, and scene reconstruction. It covers topics such as multi-view stereo, unsupervised learning for depth estimation, monocular depth estimation using deep learning, visual servoing, and the use of light field cameras for scene reconstruction.
最新文献
Open-Vocabulary Online Semantic Mapping for SLAM

article Full Text OpenAlex

Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration

book-chapter Full Text OpenAlex

IHMambaSR: An importance-guided hierarchical mamba with dynamic prompt for single image super-resolution

article Full Text OpenAlex

GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats

article Full Text OpenAlex

TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores

article Full Text OpenAlex

SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM

article Full Text OpenAlex

CGS-SLAM: Compact 3D Gaussian Splatting for Dense Visual SLAM

article Full Text OpenAlex

DR-MPC: Disturbance-Resilient Model Predictive Visual Servoing Control for Quadrotor UAV Pipeline Inspect

article Full Text OpenAlex

GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization

article Full Text OpenAlex

NeuFlow-V2: Push High-Efficiency Optical Flow To the Limit

article Full Text OpenAlex

近5年高被引文献
3D Gaussian Splatting for Real-Time Radiance Field Rendering

article Full Text OpenAlex 3690 FWCI449.2304

Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields

article Full Text OpenAlex 1509 FWCI87.0085

Plenoxels: Radiance Fields without Neural Networks

article Full Text OpenAlex 1198 FWCI69.8191

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

article Full Text OpenAlex 1149 FWCI95.9878

TrackMate 7: integrating state-of-the-art segmentation algorithms into tracking pipelines

article Full Text OpenAlex 1129 FWCI278.405

TensoRF: Tensorial Radiance Fields

book-chapter Full Text OpenAlex 1014 FWCI300.2182

Efficient Geometry-aware 3D Generative Adversarial Networks

article Full Text OpenAlex 969 FWCI80.7885

Activating More Pixels in Image Super-Resolution Transformer

article Full Text OpenAlex 917 FWCI110.6641

Resolution-robust Large Mask Inpainting with Fourier Convolutions

article Full Text OpenAlex 911 FWCI51.9062

Toward Fast, Flexible, and Robust Low-Light Image Enhancement

article Full Text OpenAlex 892 FWCI50.8285