Survey of surface reconstruction from point clouds

Get orientation of multiple objects in real-time with YOLOPose

Count crowds with multiple cameras for wider view with CVCS

Locate where in the world an image was taken with TransLocator

Track and segment occluded objects in video with occlusions-4d

Improved object orientation by doing keypoint correspondences iteratively with BD-PnP

Better weakly supervised object detection by using absolutely wrong data with NDI-WSOD

Highlight objects in image that need attention when driving with driver-gaze-yolov5

Convert nighttime infrared into daytime visible video with ROMA

Match an image taken at ground-level to an aerial photo with TransGCNN

Get orientation of object without an object model with Gen6D

Improve vision tasks with people using cells of various shapes with TCFormer

Image segmentation without labeled data using eigenvectors with deep-spectral-segmentation

Segmentation of unknown occluded object using a hierarchical model with UOAIS

Survey of 2D human pose estimation

Better predict future scene segmentation having overlapping objects with psf-diffattn

Reconstruct face with absolute dimensions from images with MICA

Real-time scene segmentation on mobile devices using feature pyramids with TopFormer

Improve scene segmentation by using region relationships with PISR

Enhance video taken with only starlight by using a physics-based noise model