Git Product home page Git Product logo

inr-harmonization's Introduction

πŸ‘‹ About Me (CV)

I received my master's degree at LEVIR Group, Beihang University (BUAA) in January 2024, supervised by Prof. Zhenwei Shi and Prof. Zhengxia Zou. Previously, I received my bachelor’s degree from Beihang University in June 2021. Besides that, I was also a research intern at SenseTime working on content generation from May - Aug, 2023, supervised by Dr. Jianlou Si. My current research interests lie in 4D (human motion) generation, AISafety, image synthesis, and remote sensing image processing.

πŸ“Ž Homepages

πŸ”₯ News

  • 2024.05: One paper is accepted by TGRS (IF=8.2)!
  • 2024.01: One paper is accepted by ICLR 2024 (Spotlight)!
  • 2023.12: One paper is accepted by TGRS (IF=8.2)!
  • 2023.10: One paper is accepted by TCSVT (IF=8.4)!
  • 2023.09: One paper is accepted by TGRS (IF=8.2)!
  • 2023.07: We have released Gradio Demo of our INR-Harmonization in Huggingface Space. Feel free to play around it πŸŽ‰πŸŽ‰!
  • 2023.06: One paper is accepted by MICCAI (STAR Award)!
  • 2023.05: Honored to be invited to give talks about Diffusion Editing and Harmonization for OPPO Research Institute!
  • 2023.05: One paper is accepted by TGRS (IF=8.2)!
  • 2023.02: 1/2 papers are accepted by CVPR 2023, and one paper is accepted by CBM (IF=7.7)!
  • 2022.12: One paper is accepted by GRSL (IF=4.8)!
  • 2022.07: One paper is accepted by TGRS (IF=8.2)!
  • 2022.06: One paper is accepted by TGRS (IF=8.2)!
  • 2022.05: Achieve the 5th place in Track I: Classification Task Defense and the 6th place in Track II: Open Set Defense, CVPR 2022 Robust Models towards Open-world Classification πŸŽ‰πŸŽ‰!

inr-harmonization's People

Contributors

windvchen avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

inr-harmonization's Issues

Can you Convert Model into ONNX ?

I was working on to convert onnx but getting too many error , @WindVChen
If possible you can define reference input and output model params because i have seen the model taking list for all image,mask,fg_coordinates but this are depent on image size so possible if will change the split_num then we will get something else input size for fg_coordinates, but you mention for loop for to get all var from datasets class that is taking the all image in dict formats having images in array .
My issue is that while taking all of static list all composite ,mask,fg_coordniate,all are in list of size 4 and having tensor with [B,C,W,H].
if possible can you help me out

Split into patches & global info

Hi,
It helps to save memory by spliting image into patches, but each patches are treated individually, is there another way to ultilize the global info of the original image for harmonization with limited GPUs?
Another question is, I'm trying to do video harmonization, sometimes the results of adjacent frames are different while the background is quite similar. Also, the same thing happens in many other works. Is it an unsolved problem for image harmonization?

about infer speed?

I didn't find anything about the speed of reasoning.What is the speed of inference

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.