Segment object by encode differences and drop duplicates with Semantic Sorting and Contrastive Flow

Improve object segmentation in video using an adaptive object proxy with AOP

Survey of semantic segmentation in urban scenes with CV-3315-Is-All-You-Need

Better multiple 3D object track and pose estimate by do it jointly with reconstruction with 3D_MOT

Improve neural surface reconstruction by using surface normals in smooth regions with NeuRIS

Better image segmentation with few examples by using multiple relevant feature maps and with MSANet

Improve human pose in complex scenes by using intra- and inter-human relationships with I2R-Net

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