Survey of super-resolution advances including diffusion and transformers

Survey of deep learning for high-resolution computer vision

Survey of crowd counting with computer vision

Video correspondence by self-supervised learning with less cost by using spatial then time with Li

Get background even when have a moving camera using transformers with DeepMCBM

Simpler unsupervised object segmentation in videos using spectral clustering with SSL-VOS

Get optical flow and object orientation even with lighting changes with INV-Flow2PoseNet

Get object orientation without training and without 3D model with PIZZA

Survey of vision transformers for action recognition

Survey of transformers for remote sensing

Improve video retrieval with text by comparing coarse and fine features with X-CLIP

Better segmentation by using the distribution of categories with MCIBI++

Get depth and new views from one image by coding for shape, appearance, pose with im2nerf

Self-supervised segmentation by students using transformers and CNN with TCC

Complete point clouds with missing data by coarse to local method with SPCNet

Improve 3D object reconstruction by using point and normal features together with PCDNF

3D object retrieval using hand sketch, text, and image inputs with Schlachter

Survey of 3D mesh denoising using geometric and learning methods

Better 3D object reconstruction with volume representations with SRDF

Improve segmentation of unknown objects by using a single stage with SOIS