Real-time object detector on the edge using better augmentation and FCOS with EdgeYOLO

Survey of real-time object detection networks including versatility, robustness, resources, energy

Survey of semantic image segmentation over two decades

Survey of facial image deblurring

Re-identify people with only bounding box annotations by spatial and occlusion contrasts with DICL

Correct fish-eye videos without jitter by weighting the time when get optical flow with SDP

Segment and complete 3D scene with unsupervised learning by fusing cross-domain features with S4R

Faster, lighter, more accurate real-time 3D object detect by early fuse 2D/3D features with TR3D+FF

Multi-person pose estimation using human and keypoint detection with two box processes with ED-Pose

Self-supervised depth estimation even in night images using illumination uncertainty with STEPS

Surface reconstruction even when occlusion by using density with volume rendering with NeuS

Survey of surface reconstruction from point clouds with Sulzer

Monocular 3D reconstruction using Chamfer distance twice with CD2

Survey of visual anomaly detection in industrial manufacturing using deep learning

Detect and segment unknown objects with unsupervised learning using graph partitioning with CutLER

Get object pose that is consistent with the input and is unique with C-3PO

Point cloud analysis with unsupervised learning using simple contrastive learning with Jiang

Detect unknown objects and attributes better by jointly training on both tasks with OvarNet

Unsupervised monocular depth estimation by optimizing with knowledge from Flow-Net with FG-Depth

Survey of 6D pose and shape estimation