HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sun, 23 Nov 2025 17:30:19 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"692344ab-29b9"
expires: Sun, 28 Dec 2025 22:03:44 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: D072:292AC1:80530F:900997:6951A6DB
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 21:53:45 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210078-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766958825.873632,VS0,VE208
vary: Accept-Encoding
x-fastly-request-id: d3d1437e08fc42184a33a0e51f9edd973ac62e57
content-length: 2744
Jixuan Fan
News
2025.06: Momentum-GS is
accepted to ICCV, 2025.
2024.07: DDIR is accepted to ECCV, 2024.
Publications and Preprints
* indicates equal contribution
Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene
Reconstruction
Jixuan Fan* ,
Wanhua Li *,
Yifei Han,
Tianru Dai,
Yansong Tang
International Conference on Computer Vision (ICCV ) , 2025
[arXiv] [Code] [Project Page]
We propose Momentum-GS, a novel approach that leverages hybrid representations for large-scale 3D
scene reconstruction.
Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary
Super-Resolution
Zhiheng Li ,
Muheng Li ,
Jixuan Fan ,
Lei Chen ,
Yansong Tang , Jie Zhou ,
and Jiwen Lu
The European Conference on Computer Vision (ECCV ) , 2024
[Paper]
[Code]
We propose the RealArbiSR dataset as a new benchmark for real-world scale arbitrary
super-resolution, along with the Dual-level Deformable Implicit Representation (DDIR) to address
this problem.
DJI, Shenzhen, China. January, 2025 - Present.
Project: 3D large-scale scene reconstruction.
© Jixuan Fan | Last updated: July 2025
