Improve segmentation of close objects in video using optical flow with BATMAN BATMAN: Bilateral Attention Transformer in...

Complete sparse depth maps from many domains by training on simulated gaps with FillDepth Towards Domain-agnostic Depth Completion arXiv...

Survey of small object detection Towards Large-Scale Small Object Detection: Survey and Benchmarks arXiv paper abstract...

Segment an object into parts with only one example by using GAN with PFTGAN Leveraging GAN Priors for Few-Shot Part Segmentation arXiv...

Better object segmentation in video by using only high quality memorized frames with QDMN Learning Quality-aware Dynamic Memory for Video...

Improve 3D object detection by using 3D equivariant neural network with DEVIANT DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D...

Detect unknown 3D objects in new domains using simulated training data with SemAbs Semantic Abstraction: Open-World 3D Scene...

Separate one image into moving and non-moving parts then do segmentation or editing with see3d Seeing 3D Objects in a Single Image via...

Better 3D object reconstruction by segmentation to learn signed distance functions with ObjectSDF Object-Compositional Neural Implicit...

Improved object segmentation using feature and mask guidance with IS-Net Highly Accurate Dichotomous Image Segmentation arXiv paper...

Locate and segment atypical objects better by being instance-aware Instance-Aware Observer Network for Out-of-Distribution Object...

Get pose in multi-person motion with occlusion by using identify and trajectory with D-MAE A Dual-Masked Auto-Encoder for Robust Motion...

Get location of panoramic camera in a 3D point cloud using color histograms with CPO CPO: Change Robust Panorama to Point Cloud...

Handle object segmentation in long videos using working and long-term memories with XMem XMem: Long-Term Video Object Segmentation with...

Detect more objects when only using image-level labels with WS-DETR Scaling Novel Object Detection with Weakly Supervised Detection...

YOLOv7 object detector has best accuracy among all real-time detectors at 30 FPS or faster YOLOv7: Trainable bag-of-freebies sets new...

Self-supervised learning using video by using optical flow to track points with PiCo Pixel-level Correspondence for Self-Supervised...

Get 3D scene, segmentation, and scene completion from one image using 3D context with MonoScene MonoScene: Monocular 3D Semantic Scene...

Align two point clouds by using an intermediate image with ImLoveNet ImLoveNet: Misaligned Image-supported Registration Network for...

Get better segmented bird's-eye view of a scene by using multiple cameras with CoBEVT CoBEVT: Cooperative Bird's Eye View Semantic...