Fix noisy dark image and change after the fact camera viewpoint, focus, exposure, tones with RawNeRF

Better object detection with semi-supervised training by using offline out-of-domain with Liu

Improve pose estimation for small-scale persons using head and body centers with Cheng

Survey of semi-supervised and unsupervised deep learning for computer vision

Survey of real-time object detection networks

Turn any human pose estimation using images to use video for better performance with simple PoseBERT

Survey of synthetic data in human analysis

Better detection of multiple objects when only using image-level labels with WSCL

Matching 3D point clouds with lie algebra

Segment scene in new target domain with unsupervised learning by paste target into source with EHTDI

Segment scene using words in the caption using one stage with PPMN

Survey of transformers for 3D vision

Image classification and object detection for low-resolution images and small objects with SPD-Conv

Better depth from monocular image by reasoning globally and locally with MonoViT

Improve segmentation of occluded objects by using 2 layers to model occlusion with BCNet

Survey of human action recognition using deep learning

Better matching of partial 3D point clouds by using uncertainty with UTOPIC

Reconstruct 3D unknown object from a single view by mapping image to points with ZeroMesh

Improve 3D human reconstruction by using occupancy planes with OPlanes

Better object detection with few examples by using image rather than proposals with Meta-DETR