Marcos V. Conde

About

Marcos V. Conde works in ML & data science and AI engineering, based in Germany - Japan (h2oai @sony @cidautai). PhD in AI and Computer Vision. Interested in neural networks, cameras and generative AI. Kaggle Grandmaster at @h2oai. Public projects on GitHub include InstructIR ([ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions…), Swin2Sr ([ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration) and AISP (AI Image Signal Processing and Computational Photography), mostly written in Jupyter and Python.

Projects 6

• 

  InstructIR

  [ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR

  github.com
• 

  Swin2Sr

  [ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. Advances in Image Manipulation (AIM) workshop ECCV 2022. Try it out! over 3.3M runs https://replicate.com/mv-lab/swin2sr

  github.com
• github.com

  AISP

  AI Image Signal Processing and Computational Photography. Official library for NTIRE (CVPR) and AIM (ICCV/ECCV) Challenges. You will find Learned ISPs, RAW Restoration-Upsampling-Reconstruction, Image Enhancement, Bokeh rendering and more!

• github.com

  Nilut

  [AAAI 2024] NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement. Project Website https://mv-lab.github.io/nilut/

• 

  Youtube8M 19

  Google Research 3rd YouTube-8M Video Understanding Challenge 2019. Temporal localization of topics within video. International Conference on Computer Vision (ICCV) 2019.

  github.com
• 

  Commonlit Readability Nlp

  CommonLit Readability Prize 2021. NLP competition hosted at Kaggle: https://www.kaggle.com/c/commonlitreadabilityprize/. Rate the complexity of literary passages for grades 3-12 classroom use

  github.com