Research
My research interests are in computational imaging and computer vision. I am interested in
identifying visible hints offered by our physical surroundings such as interreflections, and
developing imaging systems extending the visibility far beyond human ability such as the
reconstruction of objects that are not in the direct line of sight or those with strong
self-occlusions.
|
|
Novel-View Acoustic Synthesis from 3D Reconstructed Rooms
Byeongjoo Ahn,
Karren Yang,
Brian Hamilton,
Jonathan Sheaffer,
Anurag Ranjan,
Miguel Sarabia,
Oncel Tuzel,
Jen-Hao Rick Chang
Interspeech, 2024
[code]
[paper]
[video] (headset recommended)
We unmute novel-view synthesis by estimating the spatial sound anywhere in a scene containing multiple unknown sound sources, by combining blind audio recordings with 3D scene information.
|
|
Neural Kaleidoscopic Space Sculpting
Byeongjoo Ahn,
Michael De Zeeuw,
Ioannis Gkioulekas,
Aswin C. Sankaranarayanan
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[project
page]
[paper]
[supplement]
[video]
[code]
[bibtex]
We introduce a method that recovers full-surround 3D reconstructions from a single kaleidoscopic image by sculpting a neural surface representation.
|
|
Kaleidoscopic Structured Light
Byeongjoo Ahn,
Ioannis Gkioulekas,
Aswin C. Sankaranarayanan
ACM Transactions on Graphics (Proc. SIGGRAPH ASIA), 2021
[project
page]
[paper]
[video]
[bibtex]
We introduce a kaleidoscopic structured light system that generates hundreds of virtual projectors
and cameras for full surround 3D scans of intricate objects.
|
|
Convolutional Approximations to the General Non-Line-of-Sight Imaging Operator
Byeongjoo Ahn,
Akshat Dave,
Ashok
Veeraraghavan,
Ioannis Gkioulekas,
Aswin C. Sankaranarayanan
IEEE/CVF International Conference on Computer Vision (ICCV), 2019  
(Oral Presentation)
[project page]
[paper]
[supplement]
[bibtex]
A computationally efficient technique for NLOS imaging based on a derivation that shows the Gram of
the measurement operator is convolutional.
|
|
Occlusion-Aware Video Deblurring with a New Layered Blur Model
Byeongjoo Ahn,
Tae Hyun Kim,
Wonsik Kim,
Kyoung Mu Lee
Technical Report, 2016
[paper]
[bibtex]
Occlusion-aware deblurring method for scenes with occluding objects using a carefully designed
layered blur model that reflects actual blur generation process.
|
|
Reduced Illumination Patterns for Acquisition of Specular and Diffuse Normal Maps
Byeongjoo Ahn,
Junghyun Cho,
Taekyung Yoo,
Ig-Jae Kim
ACM SIGGRAPH Asia Posters, 2016
[paper]
[bibtex]
Acquisition of specular and diffuse normal maps from minimal number of polarized images by removing
the redundancy in four reflectances under XYZ-gradient and constant patterns.
|
|
Dynamic Scene Deblurring
Tae Hyun Kim,
Byeongjoo Ahn,
Kyoung Mu Lee
IEEE International Conference on Computer Vision (ICCV), 2013
[paper]
[bibtex]
Dynamic scene deblurring method estimating the latent image as well as different blur motions and
their soft segmentations jointly.
|
Services
- Area Chair, NeurIPS 2024
- Program Committee, ICCP
- Reviewer, CVPR, ICCV, ECCV, BMVC, ICLR, NeurIPS, SIGGRAPH, SIGGRAPH ASIA, TIP, TCI
- Volunteer, Camera Building Workshop as part of Gelfand Outreach Program at CMU
(2019)
- Student Volunteer, ACCV 2012, ICCP 2021
|
|