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...

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...

Remove image noise by adjust for that image a neural network trained on other data Adaptive Denoising via GainTuning arXiv paper abstract...

Unsupervised segmentation of image into parts Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP...

Convert face images into speech waveforms Facetron: Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations arXiv...

Aligning 3D points when there are large rotations and translations Registration of 3D Point Sets Using Correntropy Similarity Matrix...

Improve resolution of image when noise unknown by training with artificial data Real-ESRGAN: Training Real-World Blind Super-Resolution...

Find moment in video matching a description QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries arXiv...

Face.evoLVe: Face Recognition Library (align, detect, augment, ResNet, DenseNet, MobileNet, etc.) Face.evoLVe: A High-Performance Face...

YOLOX is best YOLO object detector and has simpler design YOLOX: Exceeding YOLO Series in 2021 arXiv paper abstract...

Cut out soft foreground in natural image with deep learning Deep Automatic Natural Image Matting arXiv paper abstract...

Correcting over-exposed image by combine many images using texture Attention-Guided Progressive Neural Texture Fusion for High Dynamic...

Get observer movement with less image data more accurately by reinforcement learning RAM-VO: Less is more in Visual Odometry arXiv paper...

Facial feature for image retrieval and for copying to another image Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval...

Tracking flexible surfaces in monocular video NRST: Non-rigid Surface Tracking from Monocular Video arXiv paper abstract...

Comparing 7 super-resolution methods for video surveillance Effectiveness of State-of-the-Art Super Resolution Algorithms in Surveillance...

Find defects in part images when only train with defect-free images Towards Total Recall in Industrial Anomaly Detection arXiv paper...