Real-time 3D human pose on mobile devices using human model with BlazePose GHUM Holistic

Get distance of far objects by using reference objects with R4D

Unknown object detection by training with phrase and region pairs with GLIP

Predict future depth and motion using only self-supervised raw images as input

Improve neural surface reconstruction by modeling high-frequency details with HFS

Get 3D mesh of head that is realistic using one image with ROME

Real-time detection of 3D planes in video by merging observations with PlanarRecon

Detect 3D shapes of objects and their 3D locations from one image with USL

3D object reconstruction from 2-3 images using geometry reasoning with SparseNeuS

Better small object detection by using Wasserstein distance with NWD

Detect image anomalies from many classes using one model with UniAD

Improve monocular 3D depth using fusion of estimated depth over time with PRT-Fusion

Get better depth from monocular images by using segmentation masks with MaskDepth

Get improved room layout from image by using pixel meaning with SRW-Net

Better image classification in new domain by focusing on foreground with RobustViT

Train 3D segmentation network using simple bounding boxes with Box2Mask

Improve 3D scene reconstruction using monocular depth and normal cues with MonoSDF

Get 3D object from images captured under unknown conditions in the wild with SAMURAI

Adapt visual tasks to new domain without source domain data with DistillAdapt

Better object pose and tracking by propagating keypoints with CenterPoseTrack