Get improved room layout from image by using pixel meaning with SRW-Net Semantic Room Wireframe Detection from a Single View arXiv paper...

Better image classification in new domain by focusing on foreground with RobustViT Optimizing Relevance Maps of Vision Transformers...

Train 3D segmentation network using simple bounding boxes with Box2Mask Semantic Instance Segmentation of 3D Scenes Through Weak Bounding...

Improve 3D scene reconstruction using monocular depth and normal cues with MonoSDF MonoSDF: Exploring Monocular Geometric Cues for Neural...

Get 3D object from images captured under unknown conditions in the wild with SAMURAI SAMURAI: Shape And Material from Unconstrained...

Adapt visual tasks to new domain without source domain data with DistillAdapt DistillAdapt: Source-Free Active Visual Domain Adaptation...

Better object pose and tracking by propagating keypoints with CenterPoseTrack Keypoint-Based Category-Level Object Pose Tracking from an...

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

3D object pose from video scan without CAD model or training with OnePose OnePose: One-Shot Object Pose Estimation without CAD Models...

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...

Survey of learning from only a few examples with computer vision applications A Comprehensive Survey of Few-shot Learning: Evolution,...

Survey of filling in missing depth data using deep learning Deep Depth Completion: A Survey arXiv paper abstract...

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...