The authors address dynamic view synthesis from a monocular video captured by a static camera, where no multi-view geometry is available.
Synthetic multi-view supervision enables 4D rendering from static camera video
ProDyGS uses depth-guided proxy images to train a deformable 3D Gaussian representation without requiring camera motion or multi-view input.
Academic
Ugo Leone Cavalcanti · Fabio Tosi · Matteo Poggi · Andrea Conti · Vladimir Zlokolica · Valerio Cambareri · +1 more
University of Bologna · Sony Depthsensing Solutions
Research Digest··3 min read
ProDyGS is a dynamic Gaussian splatting method for novel view synthesis from a single static camera video.
Why this paper
From University of Bologna and Sony Depthsensing Solutions
In one line
Depth-warped proxy views enable dynamic 3D Gaussian Splatting from one static-camera video, outperforming DyNeRF approaches that use stronger scene-flow priors.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§