Image de couverture de livre

Benchmarking the Robustness of Optical Flow Estimation to Corruptions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yi, Zhonghua, Shi, Hao, Jiang, Qi, Gao, Yao, Wang, Ze, Zhang, Yufan, Yang, Kailun, Wang, Kaiwei
Format:	Preprint
Publié:	2024
Sujets:	Image and Video Processing Computer Vision and Pattern Recognition Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data
par: Yi, Zhonghua, et autres
Publié: (2024)

Towards Anytime Optical Flow Estimation with Event Cameras
par: Ye, Yaozu, et autres
Publié: (2023)

P2U-SLAM: A Monocular Wide-FoV SLAM System Based on Point Uncertainty and Pose Uncertainty
par: Zhang, Yufan, et autres
Publié: (2024)

LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments
par: Wang, Ze, et autres
Publié: (2023)

Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis
par: Qian, Xiaolong, et autres
Publié: (2026)

Representing Domain-Mixing Optical Degradation for Real-World Computational Aberration Correction via Vector Quantization
par: Jiang, Qi, et autres
Publié: (2024)

EgoEV-HandPose: Egocentric 3D Hand Pose Estimation and Gesture Recognition with Stereo Event Cameras
par: Wang, Luming, et autres
Publié: (2026)

Exploring Event-based Human Pose Estimation with 3D Event Representations
par: Yin, Xiaoting, et autres
Publié: (2023)

Exploring Quasi-Global Solutions to Compound Lens Based Computational Imaging Systems
par: Gao, Yao, et autres
Publié: (2024)

QuaDreamer: Controllable Panoramic Video Generation for Quadruped Robots
par: Wu, Sheng, et autres
Publié: (2025)

Seeing Clearly and Deeply: An RGBD Imaging Approach with a Bio-inspired Monocentric Design
par: Yu, Zongxi, et autres
Publié: (2025)

Towards Single-Lens Controllable Depth-of-Field Imaging via Depth-Aware Point Spread Functions
par: Qian, Xiaolong, et autres
Publié: (2024)

Event-aided Semantic Scene Completion
par: Guo, Shangwei, et autres
Publié: (2025)

OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera
par: Shi, Hao, et autres
Publié: (2025)

E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes
par: Zhai, Jiajun, et autres
Publié: (2026)

Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers
par: Jiang, Qi, et autres
Publié: (2023)

EgoEvGesture: Gesture Recognition Based on Egocentric Event Camera
par: Wang, Luming, et autres
Publié: (2025)

Event-guided 3D Gaussian Splatting for Dynamic Human and Scene Reconstruction
par: Yin, Xiaoting, et autres
Publié: (2025)

Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer
par: Shi, Hao, et autres
Publié: (2022)

OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
par: Luo, Kai, et autres
Publié: (2025)

E-3DGS: Gaussian Splatting with Exposure and Motion Events
par: Yin, Xiaoting, et autres
Publié: (2024)

Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving
par: Shi, Hao, et autres
Publié: (2024)

GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Construction
par: Li, Siyu, et autres
Publié: (2024)

Design, analysis, and manufacturing of a glass-plastic hybrid minimalist aspheric panoramic annular lens
par: Gao, Shaohua, et autres
Publié: (2024)

Omnidirectional Multi-Object Tracking
par: Luo, Kai, et autres
Publié: (2025)

CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity
par: Shi, Hao, et autres
Publié: (2023)

OmniLens: Towards Universal Lens Aberration Correction via LensLib-to-Specific Domain Adaptation
par: Jiang, Qi, et autres
Publié: (2024)

MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model
par: Zeng, Kang, et autres
Publié: (2024)

Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation
par: Zhang, Jiaming, et autres
Publié: (2022)

Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers
par: Jiao, Jianbin, et autres
Publié: (2024)

$M^2$-Occ: Resilient 3D Semantic Occupancy Prediction for Autonomous Driving with Incomplete Camera Inputs
par: Lin, Kaixin, et autres
Publié: (2026)

DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Construction
par: Li, Siyu, et autres
Publié: (2024)

Towards Consistent Object Detection via LiDAR-Camera Synergy
par: Luo, Kai, et autres
Publié: (2024)

CFMW: Cross-modality Fusion Mamba for Robust Object Detection under Adverse Weather
par: Li, Haoyuan, et autres
Publié: (2024)

NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving
par: Luo, Kai, et autres
Publié: (2026)

RoHOI: Robustness Benchmark for Human-Object Interaction Detection
par: Wen, Di, et autres
Publié: (2025)

OccTrack360: 4D Panoptic Occupancy Tracking from Surround-View Fisheye Cameras
par: Lin, Yongzhi, et autres
Publié: (2026)

DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion
par: Jiao, Jianbin, et autres
Publié: (2025)

Skeleton-Based Human Action Recognition with Noisy Labels
par: Xu, Yi, et autres
Publié: (2024)

Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrations
par: Jiang, Qi, et autres
Publié: (2022)