Real-time YOLOP detects traffic object, drivable area, and road lane YOLOP: You Only Look Once for Panoptic Driving Perception arXiv...

Find location of image anomalies using neural net trained on simulated anomalies DRÆM -- A discriminatively trained reconstruction...

Better 3D reconstruction without exact model match by using database of patches Patch2CAD: Patchwise Embedding Learning for In-the-Wild...

Improve thermal IR images using neural net to model physics and influence of scene Thermal Image Processing via Physics-Inspired Deep...

Detect anomaly in video by reconstructing motion and frame predicting A Hybrid Video Anomaly Detection Framework via Memory-Augmented...

Segmentation system marks unknown objects which are then incrementally learned Deep Metric Learning for Open World Semantic Segmentation...

Segment humans in image after self-supervised training on multiple views Self-supervised Human Detection and Segmentation via Multi-view...

Segmenting objects in images with transformers SOTR: Segmenting Objects with Transformers arXiv paper abstract...

Dense depth in crowded dynamic scenes using sparse depth and monocular color images DnD: Dense Depth Estimation in Crowded Dynamic Indoor...

Get segmented bird's-eye view of a scene from one frontal image Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images...

Building detection in high-resolution satellite images Continental-Scale Building Detection from High Resolution Satellite Imagery arXiv...

Image retrieval using an image and a description of what to modify Image Retrieval on Real-life Images with Pre-trained...

Remove haze in a single image by using three components From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data...

Get depth in videos where the objects and the camera move Consistent Depth of Moving Objects in Video arXiv paper abstract...

Make high dynamic range image from low dynamic range images with fewer artifacts Wavelet-Based Network For High Dynamic Range Imaging...

Train thermal image tracker on plentiful RGB images for better performance Unsupervised Cross-Modal Distillation for Thermal Infrared...

Robust fast tracking using multi-level feature transformer HiFT: Hierarchical Feature Transformer for Aerial Tracking arXiv paper...

Good and fast 3D object detection by using simulated depth data Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images...

Improve 3D depth estimates by using relationships between objects Probabilistic and Geometric Depth: Detecting Objects in Perspective...

Making blueprints from images of carpentered items Fabrication-Aware Reverse Engineering for Carpentry arXiv paper abstract...