Git Product home page Git Product logo

radiancemapping's Introduction

Bio.

I am a third-year PhD at Shanghai Jiao Tong University, advised by Prof. Bingbing Ni. I received BEng degree from the same university. I have published several papers on prestigious venues, e.g., CVPR, ICLR, AAAI, JBHI, NeurIPS and MICCAI, one of which is selected as CVPR 2023 Highlight (2.5% of submissions). I serve as the reviewer of CVPR, ECCV, ICCV, NeurIPS, AAAI, MICCAI, etc. I was awarded Bosch 2021 AIOT scholarship (50 recipients worldwide) and MICCAI 2019 Undergraduate Student Travel Award. I also host MICCAI 2020 RibFrac Challenge as organizer.

My research interests center around 3D vision, neural rendering and shape analysis. Currently, I have been primarily investigating neural rendering and 3D reconstruction.

Research Projects

Publications

  • FreqPCR: [CVPR 2023 Highlight (10% of accepted papers)] Frequency-Modulated Point Cloud Rendering with Easy Editing
  • RadianceMapping: [AAAI 2023] Boosting Point Clouds Rendering via Radiance Mapping
  • AudioEar: [AAAI 2023] AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audio
  • RASF: [ICLR 2023] Representation-Agnostic Shape Fields
  • ACSConv: [IEEE JBHI] Reinventing 2D Convolutions for 3D Images

Preprint / Technical Reports

  • Uncertainty Quantification: [ArXiv] Evaluating and Boosting Uncertainty Quantification in Classification
  • RibFrac: [MICCAI Challenge] A challenge for rib fracture detection and classification

Educational Projects

radiancemapping's People

Contributors

seanywang0408 avatar yizhangphd 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

Watchers

 avatar  avatar

Forkers

fanwei360

radiancemapping's Issues

rename select.py

/bpcr/lib/python3.8/subprocess.py", line 64, in <module>
    import msvcrt

ModuleNotFoundError: No module named 'msvcrt'



/bpcr/lib/python3.8/subprocess.py", line 70, in <module>
    import select

Rename select.py to another name to solve this issue due to complicit with import select

NeRF synthetic points

Hi, I notice that you mention Nerf-synthetic points genertated from Point-NeRF

NeRF-Synthetic: Please download dataset from NeRF and put the unpacked files in ./data/nerf_synthetic. To generate point clouds, run Point-NeRF and save the point clouds in ./data/pc/nerf.

However, Point-NeRF env is hard to configure. So, I utilize the points generated from vanilla-nerf, but the PSNR is very slow about 15db after training 200k. I think the coordinate or something different compared with your ./data/pc/nerf.

So, Can you share me ./data/pc/nerf ?
Thanks in advance.

torch version problem

Installation in Readme.md

conda install pytorch==1.8.0 torchvision==0.9.0 cudatoolkit=10.2 -c pytorch

I think this should be

conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=10.2 -c pytorch

because of the requirement piqa need torch>=1.12.0 and torchvision>=0.13.0

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.