Every moment of a scene, visible at once
Bilawal Sidhu reconstructs a geolocated 2D video as per-frame 3D, so a dog’s whole path through the shot exists in space at once — Vonnegut’s Tralfamadorians, applied to four legs.
A normal video is a sequence. This one is a volume. Bilawal Sidhu takes a geolocated 2D clip and reconstructs it per frame in 3D, so the dog does not move through the shot. The shot contains the dog's entire path at once.
The Vonnegut line is doing real work. In Slaughterhouse-Five, Tralfamadorians see humans as long millipedes of every moment they will ever occupy. The reconstruction makes that metaphor literal, and a four-legged gait leaves a trail you can actually read.
The impressive part is not a filter. A phone-shaped video now has a spatial axis you can inspect from the side.
Bilawal Sidhu
@bilawalsidhu
Space and time reconstructed in 4D Is this how higher dimensional beings see us - every moment at once? Starting to understand what Vonnegut meant by humans being “great millipedes” - clearly it applies to our four legged friends too! Geolocated 2d video → per frame 3d https://t.co/b26zqfOFWC
57.8K likes
- likes
- 57,840
- replies
- 976
Captured when this was curated, not live. —
