Combine knowledge of many vision transformers into a smaller multi-talented model Knowledge Amalgamation for Object Detection with...

Improve segmentation in bin picking by using part awareness Towards Robust Part-aware Instance Segmentation for Industrial Bin Picking...

Get 3D layout of room from a panoramic image with LGT-Net LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware...

Convert a blurry image to a sharp video using a continuous intensity function with E-CIR E-CIR: Event-Enhanced Continuous Intensity...

Survey of continuous human action recognition Continuous Human Action Recognition for Human-Machine Interaction: A Review arXiv paper...

Survey of re-identifying people seen by multiple cameras for various problem types Person Re-identification: A Retrospective on Domain...

Real-time object segmentation in video with faster training using EfficientVIS Efficient Video Instance Segmentation via Tracklet Query...

Better recognition of human actions using two-stage detection transformers Efficient Two-Stage Detection of Human-Object Interactions...

Improve scene segmentation with smaller models by distilling knowledge with SKR+PEA Transformer-based Knowledge Distillation for...

Estimate the pixel map homograhy using image features and pixels Towards a Unified Approach to Homography Estimation Using Image Features...

Segment objects of any type in image using model trained without manual annotations with FreeSOLO FreeSOLO: Learning to Segment Objects...

Better object detection when domain change with balanced domains using BD-DIR Domain-Invariant Proposals based on a Balanced Domain...

Improve object discovery with self-supervised transformers using TokenCut Self-Supervised Transformers for Unsupervised Object Discovery...

Better image stitching by using depth information Natural Image Stitching Using Depth Maps arXiv paper abstract...

Improve any image feature matcher on large appearance changes using OETR Guide Local Feature Matching by Overlap Estimation arXiv paper...

Human pose estimation with %80 smaller model and 68% less CPU using STNet Towards Simple and Accurate Human Pose Estimation with Stair...

Improve vision models by pretrain on uncurated images without supervision with SEER Vision Models Are More Robust And Fair When...

Better 3D surface reconstruction from point clouds by using sensor's viewpoint Deep Surface Reconstruction from Point Clouds with...

Remove haze in a single image using estimated transmission map with EDN-GTM A Novel Encoder-Decoder Network with Guided Transmission Map...

Improved object detection when test and train domains differ with MS-DAYOLO Integrated Multiscale Domain Adaptive YOLO arXiv paper...