Improve human motion estimate in video using physics with HUND+SO+GT+Dynamics Trajectory Optimization for Physics-Based Reconstruction of...

Explain image classifier by showing features in source and target domains with XSDA-Net Explainable Supervised Domain Adaptation arXiv...

Enhance dark images in new untrained domain by simulating image pipeline for training Towards Robust Low Light Image Enhancement arXiv...

Classify small images accurately using little memory and CPU with ImageSig ImageSig: A signature transform for ultra-lightweight image...

Better object segmentation of unknown objects using region awareness with RAML Region-Aware Metric Learning for Open World Semantic...

3D object reconstruction using a few views despite noisy camera poses with FvOR FvOR: Robust Joint Shape and Pose Optimization for...

Improve 3D object reconstruction using unsupervised learning on image collection with TARS Topologically-Aware Deformation Fields for...

3D shape, segmentation, appearance, and object poses from images using neural fields with PNF Panoptic Neural Fields: A Semantic...

Better segment aerial photo by learning multi-resolution features with IFWM Improved-Flow Warp Module for Remote Sensing Semantic...

Count crowds accurately even after add new domain with FLCB Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning...

Survey of surface reconstruction from point clouds Surface Reconstruction from Point Clouds: A Survey and a Benchmark arXiv paper...

Get orientation of multiple objects in real-time with YOLOPose YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint...

Locate where in the world an image was taken with TransLocator Where in the World is this Image? Transformer-based Geo-localization in...

Track and segment occluded objects in video with occlusions-4d Revealing Occlusions with 4D Neural Fields arXiv paper abstract...

Improved object orientation by doing keypoint correspondences iteratively with BD-PnP Coupled Iterative Refinement for 6D Multi-Object...

Better weakly supervised object detection by using absolutely wrong data with NDI-WSOD Absolute Wrong Makes Better: Boosting Weakly...

Highlight objects in image that need attention when driving with driver-gaze-yolov5 Where and What: Driver Attention-based Object...

Convert nighttime infrared into daytime visible video with ROMA ROMA: Cross-Domain Region Similarity Matching for Unpaired Nighttime...

Match an image taken at ground-level to an aerial photo with TransGCNN Transformer-Guided Convolutional Neural Network for Cross-View...

Get orientation of object without an object model with Gen6D Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images...