Skip to content
@OpenImagingLab

OpenImagingLab

README.md

Welcome to OpenImagingLab! 👋

The OpenImagingLab is a research group from Shanghai AI Lab. We are dedicated to utilizing advanced AI algorithms to research and design innovative AI vision sensors, image processing pipeline, optical components, camera systems and brain-inspired computing hardware for AI-ISP. Leveraging deep learning and generative AI, the team aims to develop next-generation systems suitable for image capture and 3D imaging.



We are looking for self-motivated Interns and Joint Training PhD Students (Details), who are interested in computational photography, computer vision and computer graphics. Email:openimaginglab@pjlab.org.cn

Popular repositories Loading

  1. HDRFlow HDRFlow Public template

    [CVPR 2024] Real-Time HDR Video Reconstruction

    Python 163 6

  2. DualDn DualDn Public

    [ECCV2024] DualDn: Dual-domain Denoising via Differentiable ISP. ⭐😤⭐💀 SOTA model for real-image denoising. 💀 Both in terms of denoising performance and generalization ability.

    Python 71 2

  3. UltraFusion UltraFusion Public

    [CVPR 2025 Highlight] UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion

    Python 66 4

  4. emm emm Public

    [ECCV2024] Event-Based Motion Magnification

    Python 60 3

  5. AdaptiveISP AdaptiveISP Public

    [NeurIPS2024] AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection

    Python 32 5

  6. Sim2Real Sim2Real Public

    [SIGGRAPH Asia 2024] From Sim to Real: Toward General Event-based Low-Light Frame Interpolation with Per-scene Optimization

    Python 27 4

Repositories

Showing 10 of 19 repositories
  • 4DSloMO Public
    OpenImagingLab/4DSloMO’s past year of commit activity
    0 0 0 0 Updated Jun 30, 2025
  • UltraFusion Public

    [CVPR 2025 Highlight] UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion

    OpenImagingLab/UltraFusion’s past year of commit activity
    Python 66 GPL-3.0 4 6 0 Updated Jun 13, 2025
  • DualDn Public

    [ECCV2024] DualDn: Dual-domain Denoising via Differentiable ISP. ⭐😤⭐💀 SOTA model for real-image denoising. 💀 Both in terms of denoising performance and generalization ability.

    OpenImagingLab/DualDn’s past year of commit activity
    Python 71 2 1 0 Updated May 27, 2025
  • Sim2Real Public

    [SIGGRAPH Asia 2024] From Sim to Real: Toward General Event-based Low-Light Frame Interpolation with Per-scene Optimization

    OpenImagingLab/Sim2Real’s past year of commit activity
    Python 27 MIT 4 4 0 Updated May 22, 2025
  • S2R-HDR Public

    S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion

    OpenImagingLab/S2R-HDR’s past year of commit activity
    Python 5 0 0 0 Updated May 16, 2025
  • EGVD Public

    This is the official code for the paper "EGVD: Event-Guided Video Diffusion Model for Physically Realistic Large-Motion Frame Interpolation". The code will be made public when the paper is accepted.

    OpenImagingLab/EGVD’s past year of commit activity
    Python 11 0 1 0 Updated May 14, 2025
  • PhoCoLens Public

    PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging

    OpenImagingLab/PhoCoLens’s past year of commit activity
    Python 20 1 2 0 Updated Mar 29, 2025
  • PSF-Estimation Public

    [CVPR2025] A Physics-Informed Blur Learning Framework for Imaging Systems

    OpenImagingLab/PSF-Estimation’s past year of commit activity
    MATLAB 16 5 3 0 Updated Mar 20, 2025
  • RLPixTuner Public

    [NeurIPS 2024] Goal Conditioned Reinforcement Learning for Photo Finishing Tuning

    OpenImagingLab/RLPixTuner’s past year of commit activity
    Python 26 1 4 0 Updated Mar 19, 2025
  • AdaptiveISP Public

    [NeurIPS2024] AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection

    OpenImagingLab/AdaptiveISP’s past year of commit activity
    Python 32 5 1 0 Updated Feb 18, 2025
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…