Answering spatial questions about scene using image and 3D with ScanQA ScanQA: 3D Question Answering for Spatial Scene Understanding...

Sharper depth from single image by using scene structure and details with CADepth-Net Channel-Wise Attention-Based Network for...

Accurate facial computer vision with Microsoft system trained only on artificial images Fake It Till You Make It: Face analysis in the...

Untrained object detection using over 100 times less data by flexible captioning with OTTER Data Efficient Language-supervised Zero-shot...

Survey of methods for detecting new objects with only a few examples Few-Shot Object Detection: A Survey arXiv paper abstract...

Segment objects in images with arbitrary text queries using OpenSeg Open-Vocabulary Image Segmentation arXiv paper abstract...

Reidentify people in new scenes better by accounting for camera styles with CA-UReID Camera-aware Style Separation and Contrastive...

Improved deblurring of images with guided image generation in W-DIP Wiener Guided DIP for Unsupervised Blind Image Deconvolution arXiv...

Segment object in an image according to a text description CRIS: CLIP-Driven Referring Image Segmentation arXiv paper abstract...

Improved object segmentation in video by using object descriptors instead of pixel matching HODOR: High-level Object Descriptors for...

Answer questions about scene using image and 3D information 3D Question Answering arXiv paper abstract https://arxiv.org/abs/2112.08359v1...

Get 3D shape, pose, and relative depth of people from a single image despite occlusion Putting People in their Place: Monocular...

Improved super-resolution for display screens by using transformer designed for screen content Implicit Transformer Network for Screen...

Better enhancement of dim images with edge-awareness using CSDNet Learning Deep Context-Sensitive Decomposition for Low-Light Image...

Robot grips new objects in new poses from 10 examples using neural descriptor fields Neural Descriptor Fields: SE(3)-Equivariant Object...

Recognize 3D objects when only trained on 2D image and text pairs with PointCLIP PointCLIP: Point Cloud Understanding by CLIP arXiv paper...

Track people in images better by building 3D model from image and predicting appearance Tracking People by Predicting 3D Appearance,...

Calibrate cameras from video with sub-pixel error using self-supervision Self-Supervised Camera Self-Calibration from Video arXiv paper...

Restore faces blurred by air turbulence with prior knowledge from GAN network LTT-GAN: Looking Through Turbulence by Inverting GANs arXiv...

Detect new objects better by teaching classifier not to ignore unlabeled objects Learning to Detect Every Thing in an Open World arXiv...