[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

[CVPR2023] Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

[TPAMI2023] Continual Learning for Blind Image Quality Assessment

[NeurIPS2022] Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop

LOD-PCAC: Level-of-detail-based Deep Lossless Point Cloud Attribute Compression (TIP 2025)

Repository for Zochi's Research

Academic Survey Paper Generation.

Deep Contextual Video Compression

所有小初高、大学PDF教材。

Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).

GEO-Bench: Toward Foundation Models for Earth Monitoring

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also …

Perceptual quality metrics for TensorFlow

Data compression in JAX

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Open-source implementation of JPEG2000 Part-15 (or JPH or HTJ2K)

Image transformation, compression, and decompression codecs.

Fraunhofer Neural Network Encoder/Decoder (NNCodec)

LIBPNG: Portable Network Graphics support, official libpng repository

Main libjpeg-turbo repository

AV1 Image File Format Specification - ISO-BMFF/HEIF derivative

Quality Assessment for Tone-Mapped HDR Images Using Multi-Scale and Multi-Layer Information (ICMEw 2018)