APIUp to 25% cheaper than official pricesTry the API →
Hermes
APIModelsCases
Back to News
paperVideoImage

Peking University's ATGS Reconstructs 1,400-Frame Athletic Scenes in One Shot

A new Gaussian splatting framework reconstructs volumetric videos with thousands of frames of complex motion, extending prior methods by roughly 70x in temporal coverage.

Peking University's ATGS Reconstructs 1,400-Frame Athletic Scenes in One Shot
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read

A new Gaussian splatting framework reconstructs volumetric videos with thousands of frames of complex motion, extending prior methods by roughly 70x in temporal coverage.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

UniForge3D Builds Complete 3D Models From a Few Unposed Photos
AlphaSignal · paper

UniForge3D Builds Complete 3D Models From a Few Unposed Photos

Tencent's Youtu-Parsing-Omni Turns Seven Media Types Into One JSON Output
Tencent Hy · model

Tencent's Youtu-Parsing-Omni Turns Seven Media Types Into One JSON Output

Stanford and Google's LoT Diffusion Cuts Image Tokens by 4.6x Without Losing Detail
AlphaSignal · paper

Stanford and Google's LoT Diffusion Cuts Image Tokens by 4.6x Without Losing Detail