Anand Bhattad
PhD Student
Advisor: David A. Forsyth
Computer Science Department
University of Illinois Urbana Champaign
Email /
CV /
Google Scholar
/
Twitter /
Github
|
|
|
I am a PhD student in the Computer Vision
Group at UIUC working with Prof. David A. Forsyth. I also closely collaborate with Derek Hoiem, Shenlong Wang and Yuxiong Wang. My research interests are in
computer vision and computational photography.
Earlier, I graduated from UIUC with an MS in Computer Science and fell in love with computer vision.
In my previous life, I enjoyed working on the Damage Assessment of Civil Infrastructure Systems.
During those times, I graduated from UIUC with an MS and NITK Surathal in India with a BTech in
Civil Engineering.
During my PhD, I have had the pleasure of working with
Get in touch
I am interested in an academic career and currently seeking a postdoc position starting Fall 2023.
Please email me if you think I would be a good fit for your team.
I organize computer vision speaker
series at UIUC. If you are interested in giving a talk at UIUC, please email me.
Recent and Upcoming Talks
- UC Berkeley: Vision Seminar, Apr 2023
- NVIDIA Research, Apr 2023
- MIT: Vision and Graphics Seminar, Apr 2023
- CMU: VASC Seminar, Mar 2023
- UW: Vision Seminar, Mar 2023
- UMD: Vision Seminar, Mar 2023
- UCSD: Pixel Cafe Seminar, Feb 2023
- TTIC: Research Talk, Feb 2023
|
Research
The primary aim of my research is easy and fast image editing. I create algorithms that can convincingly
insert objects cut from one or more images and pasted into another, relight single images or generate
objects and scenes from novel views. The goal is to go beyond this. One should be able to perform all these
tasks using a single framework with ease.
In the long-term, I see a neural rendering engine taking over physically based rendering engines. My
research focuses on making this vision a reality.
Publications
|
Enriching StyleGAN with Illumination Physics
Anand Bhattad,
David A. Forsyth
arXiv, 2022
arXiv
We show that by imposing known physical facts about images, the distribution of images produced by
a StyleGAN can be significantly enriched.
|
|
Image-based Object Insertion using Persistent and Transient Decomposition
Anand Bhattad,
Brian Chen,
Stephan R. Richter,
David A. Forsyth
arXiv, 2022
Coming Soon
First self-supervised, image-based object relighting method trained without labeled paired data,
CGI data, geometry, or environment maps.
|
|
SIRfyN: Single Image Relighting from your Neighbors
David A. Forsyth,
Anand Bhattad,
Pranav Asthana,
Yuani Zhong,
Yuxiong Wang
arXiv, 2022
Early Draft
First scene relighting method that requires no
labeled or paired image data.
|
|
Cut-and-Paste Object Insertion by Enabling Deep Image Prior for Reshading
Anand Bhattad,
David A. Forsyth
Internation Conference on 3D Vision (3DV), 2022
Project
Convincing cut-and-paste reshading with consistent image decomposition inferences.
|
|
DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for
Volume Rendering
Liwen Wu,
Jae Yong Lee,
Anand Bhattad,
Yuxiong Wang,
David A. Forsyth
Computer Vision and Pattern Recognition (CVPR), 2022 (Best Paper Finalist)
Project /
Training Code /
Real-time Code
Improving Real-Time NeRF with Deterministic Integration.
|
|
View Generalization for Single Image Textured 3D Models
Anand Bhattad,
Aysegul Dundar,
Guilin Liu,
Andrew Tao,
Bryan Catanzaro
Computer Vision and Pattern Recognition (CVPR), 2021
Project
Consistent textured 3D inferences from a single 2D image.
|
|
Unrestricted Adversarial Examples via Semantic Manipulation
Anand Bhattad*,
Min Jin Chong*,
Kaizhao Liang,
Bo Li,
David A. Forsyth
International Conference on Learning Representations (ICLR), 2020
CVPR-W on Adversarial ML in Real-World Computer Vision
Systems, 2019
Generating realistic adversarial examples by image re-colorization and texture transfer.
|
|
Improved Style Transfer with Calibrated Metrics
Mao Chuang Yeh*,
Shuai Tang*,
Anand Bhattad,
Chuhang Zou,
David A. Forsyth
Winter Conference on Applications of Computer Vision (WACV), 2020
A novel quantitative evaluation procedure for style transfer methods.
|
|
Detecting Anomalous Faces with "No Peeking'' Autoencoders
Anand Bhattad,
Jason Rock,
David A. Forsyth
CVPR Workshop on Vision with Biased or
Scarce Data, 2018
A simple unsupervised method for detecting anomalous faces by carefully constructing features from
"No Peeking" or inpainting autoencoders.
|
|