| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://immortalco.github.io/VirtualFittingRoom/
access-control-allow-origin: *
strict-transport-security: max-age=31556952
expires: Sun, 28 Dec 2025 11:33:06 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: 0FA1:2118F1:77D4B9:866D19:69511319
accept-ranges: bytes
date: Sun, 28 Dec 2025 11:23:06 GMT
via: 1.1 varnish
age: 0
x-served-by: cache-bom-vanm7210051-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766920986.966034,VS0,VE207
vary: Accept-Encoding
x-fastly-request-id: 3014d0a6467b2f88b84e2c54099606d968257ac6
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Thu, 04 Dec 2025 07:33:11 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"69313937-112f6"
expires: Sun, 28 Dec 2025 11:33:06 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 70CE:2685F2:77A635:863EDC:69511315
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 11:23:06 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210051-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766920986.186978,VS0,VE212
vary: Accept-Encoding
x-fastly-request-id: 63a4ed7361786db8eda4c2bb1ad76f5f161693bd
content-length: 11028
Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image
![garment]()
Garment
Generated Anchor Video
Motion Reference
![user_image]()
User
Try-On Result
Virtual Fitting Room:
Virtual Fitting Room: Generating Arbitrarily Long
Videos of Virtual Try-On from a Single Image
University of Illinois at Urbana-Champaign
SpreeAI
Virtual Fitting Room:
Generating Arbitrarily Long Videos of Virtual Try-On from a
Single
Image
Virtual Fitting Room: Generating Arbitrarily Long
Videos of Virtual Try-On from a Single Image
| Jun-Kun
Chen
|
Aayush Bansal
|
Minh Phuoc Vo
|
Yu-Xiong Wang
|
University of Illinois at Urbana-Champaign
SpreeAIOverview
We present Virtual Fitting Room, a video generation framework for creating minute-scale try-on videos from a single user image, a target garment, and a reference motion. Unlike traditional try-on methods that produce short clips or static images, VFR supports arbitrarily long, high-resolution videos with natural user-garment interactions.
Our approach segments long sequences into overlapping clips and enforces local smoothness between adjacent segments while preserving global temporal consistency using a compact anchor video. This design enables stable synthesis over extended motions without relying on long training sequences.
The generated videos exhibit appearance consistency from all viewpoints, robust handling of self-occlusions and body interactions, and preservation of fine details such as accessories. As a by-product, VFR also supports free-viewpoint rendering, enabling novel camera angles from a single input image.
Various motions.
Demo Video
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
){kind=link}
Citation
Acknowledgements
We thank you and the other visitors for visiting our project page.