Complete point clouds with very few points using Wasserstein GAN and Transformers with Wu
Get 3D models of objects in scene from multiple images without labeling by using NeRF with ONeRF
Get shape, pose, and appearance from a single image using signed distance function with Pavllo
Segment scene in new domain by combining probabilities from old domains with MDA
Improve 3D object detection by combine image and point data at many scales with ImLiDAR
Segment long videos with transformers using tracking information with ROVIS
Counting objects in image with few or zero examples using shape and image features with LOCA
3D object detection in point clouds using only 2D image labels for training with RCV
Survey of computer vision using transformers by Jamil
Better image segmentation of details by using multiple image crops with CropFormer
Improve match 3D point clouds using graph matching with RGM
Re-identify people in new domains with unsupervised learning by rewinding video with CycAs
Real-time multi-person pose estimation and tracking with AlphaPose
Better map 2D image points of people to 3D surfaces using novel loss function with UV R-CNN
Improve 3D object segmentation with scene labels by using superpoints with WHCN
Better object detection with few examples by spatial reasoning on known objects with FSOD-SR
Improve 3D object segmentation using transformers directly on point clouds with Mask3D
Survey of 3D reconstruction of non-rigid objects using monocular images
Object segmentation by label only 1 point per target when train with PSPS
Real-time 3D scene reconstruction from monocular images using SLAM for NeRF with NeRF-SLAM