Jie Hu

PE3R. [CVPR'26] PE3R: Perception-Efficient 3D Reconstruction. Take 2 - 3 photos with your phone, upload them, wait a few minutes, and then start exploring your 3D world via text!

YOSO. Code release for paper "You Only Segment Once: Towards Real-Time Panoptic Segmentation" [CVPR 2023]

ISTR. ISTR: End-to-End Instance Segmentation with Transformers (https://arxiv.org/abs/2105.00637)

PAIS. Code release for paper "Pseudo-label Alignment for Semi-supervised Instance Segmentation" [ICCV 2023]

Mini-Segment-Anything. Distilling the powerful segment anything models into lightweight ones for efficient segmentation.

MVTec-Caption. Python

VisualFeatureTranslation. The project page of paper: Towards Visual Feature Translation [CVPR 2019]

InformationCompetingProcess. The project page of paper: Information Competing Process for Learning Diversified Representations [NeurIPS 2019]

pGAN. The code of paper: Robust Face Sketch Synthesis via Generative Adversarial Fusion of Priors and Parametric Sigmoid (pGAN) [IJCAI 2018]

NAD. The project page of paper: Architecture disentanglement for deep neural networks [ICCV 2021, oral]

MDAL. The code of paper: Face Sketch Synthesis by Multidomain Adversarial Learning (MDAL) [TNN 2018]

UISE. Python