HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 08 Oct 2025 01:21:54 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"68e5bcb2-33a5"
expires: Sun, 28 Dec 2025 16:09:12 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: CD00:272D88:7D3178:8C45B4:695153CD
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 17:54:12 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210028-BOM
x-cache: HIT
x-cache-hits: 0
x-timer: S1766944453.556500,VS0,VE208
vary: Accept-Encoding
x-fastly-request-id: 9c7861140dfa76a741c08518b1495e78b3deb66f
content-length: 3530
Jiraphon Yenphraphai
Jiraphon Yenphraphai (Dome)
จิรพนธ์ เย็นพระพาย (โดม)
Hello, I'm a PhD student at Purdue University where I am advised by Raymond A. Yeh . My research focuses on the intersection of computer vision and graphics.
I am currently a research intern on the Creative Vision at Snapchat, where I work with Chaoyang Wang , Peter Wonka , and Ashkan Mirzaei .
Previously, I received my Master's degree from NYU Courant, under the supervision of Saining Xie . Earlier in my career, I was fortunate to be advised by Supasorn Suwajanakorn , with a focus on view synthesis.
My undergraduate studies were completed at Chulalongkorn University in Bangkok, Thailand.
Email /
Scholar /
Github
Research
I am interested in 3D&4D reconstruction. My past projects have centered around AI that creates images and inverse rendering to make things look real.
(* means equal contribution)
Your browser does not support the video tag.
ShapeGen4D: Towards High Quality 4D Shape Generation from Videos
Jiraphon Yenphraphai ,
Ashkan Mirzaei ,
Jianqi Chen ,
Jiaxu Zou ,
Sergey Tulyakov ,
Raymond A. Yeh ,
Peter Wonka ,
Chaoyang Wang
project page
/
arXiv
We introduce a native video-to-4D shape framework that synthesizes a single dynamic 3D representation end-to-end from the video.
Your browser does not support the video tag.
Image Sculpting: Precise Object Editing with 3D Geometry Control
Jiraphon Yenphraphai ,
Xichen Pan ,
Sainan Liu ,
Daniele Panozzo ,
Saining Xie
CVPR, 2024
project page
/
arXiv
/
video
/
code
A framework allows for detailed and realistic 3D editing from a single image, including precise pose editing, rotation, and more.
Your browser does not support the video tag.
NeX: Real-time View Synthesis with Neural Basis Expansion
Suttisak Wizadwongsa* ,
Pakkapon Phongthawee* ,
Jiraphon Yenphraphai* ,
Supasorn Suwajanakorn
CVPR, 2021 (Oral, Best paper candidate)
project page
/
arXiv
/
video
/
code
/
Two Minute Papers
The enhancements of multiplane image (MPI) that can reproduce NeXt-level view-dependent effects in real time.
Your browser does not support the video tag.
NeX360: Real-time All-around View Synthesis with Neural Basis Expansion
Pakkapon Phongthawee* ,
Suttisak Wizadwongsa* ,
Jiraphon Yenphraphai ,
Supasorn Suwajanakorn
TPAMI, 2022
project page
/
arXiv
We develop multiple MPIs for unbounded 360° scenes.
Big thank you to Jon Barron for the source code of this website.