[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Official Repo for ICCV25-Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization

Implementation of visual based UAV geo-localization using satellite imagery

[IEEE JSTARS 2024] CV-Cities: Advancing Cross-view Geo-localization in Global Cities

ACM Multimedia2020 University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization 🚁 annotates 1652 buildings in 72 universities around the world.

[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

Code release for CVPR'24 submission 'OmniGlue'

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

[CVPR 2025] JamMa is a lightweight image matcher that enables fast internal and mutual interaction of images with joint Mamba.

[DEIMv2] Real Time Object Detection Meets DINOv3

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

Effortless data labeling with AI support from Segment Anything and other awesome models.

[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Ultra-high-performance, secure, all-in-one acceleration engine for developer resources

Repository for the code related to the paper "CARDIE:clustering algorithm on relevant descriptors for image enhancement"

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

Official PyTorch implementation of the Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025).

Official PyTorch implementation of the Motion Aware Event Representation-driven Image Deblurring (ECCV 2024).

Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events

Official repository for the ECCV 2024 paper, "CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring", ECCV 2024

The official implementation of "Compositional Generative Model of Unbounded 4D Cities". (TPAMI 2026)

[ICCV 2025] STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

A generative world for general-purpose robotics & embodied AI learning.

[IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition

[ NeurIPS 2024 ] The official PyTorch implementation for Learning Truncated Causal History Model for Video Restoration.