AILab-CVC/UniRepLKNet
[CVPR 2024 & TPAMI 2025] UniRepLKNet
This project offers a unified deep learning model that processes various types of data, including images, audio, and time-series, to perform tasks like object recognition, sound classification, and environmental forecasting. It provides a single architecture that can adapt to different data without extensive customization, producing highly accurate predictions. Researchers and practitioners in fields requiring strong general perception models for diverse data will find this useful.
1,069 stars. No commits in the last 6 months.
Use this if you need a high-performing, adaptable model that can effectively analyze different data types, like images, audio, and global weather patterns, with a single unified architecture.
Not ideal if you require highly specialized, domain-specific models that are already optimized for a single data modality with unique architectural needs.
Stars
1,069
Forks
61
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/AILab-CVC/UniRepLKNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
drprojects/superpoint_transformer
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D...
yuxumin/PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
charlesq34/frustum-pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
drprojects/DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...
facebookresearch/votenet
Deep Hough Voting for 3D Object Detection in Point Clouds