Improve segmentation of close objects in video using optical flow with BATMAN

Complete sparse depth maps from many domains by training on simulated gaps with FillDepth

Survey of small object detection

Segment an object into parts with only one example by using GAN with PFTGAN

Better object segmentation in video by using only high quality memorized frames with QDMN

Improve 3D object detection by using 3D equivariant neural network with DEVIANT

Detect unknown 3D objects in new domains using simulated training data with SemAbs

Separate one image into moving and non-moving parts then do segmentation or editing with see3d

Better 3D object reconstruction by segmentation to learn signed distance functions with ObjectSDF

Improved object segmentation using feature and mask guidance with IS-Net

Locate and segment atypical objects better by being instance-aware

Get pose in multi-person motion with occlusion by using identify and trajectory with D-MAE

Get location of panoramic camera in a 3D point cloud using color histograms with CPO

Handle object segmentation in long videos using working and long-term memories with XMem

Detect more objects when only using image-level labels with WS-DETR

YOLOv7 object detector has best accuracy among all real-time detectors at 30 FPS or faster

Self-supervised learning using video by using optical flow to track points with PiCo

Get 3D scene, segmentation, and scene completion from one image using 3D context with MonoScene

Align two point clouds by using an intermediate image with ImLoveNet

Get better segmented bird's-eye view of a scene by using multiple cameras with CoBEVT