Skip to yearly menu bar Skip to main content


Spotlight Poster

DyST: Towards Dynamic Neural Scene Representations on Real-World Videos

Maximilian Seitzer · Sjoerd van Steenkiste · Thomas Kipf · Klaus Greff · Mehdi S. M. Sajjadi

Halle B #100
[ ]
Fri 10 May 1:45 a.m. PDT — 3:45 a.m. PDT

Abstract:

Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene Transformer (DyST) model leverages recent work in neural scene representation to learn a latent decomposition of monocular real-world videos into scene content, per-view scene dynamics, and camera pose. This separation is achieved through a novel co-training scheme on monocular videos and our new synthetic dataset DySO. DyST learns tangible latent representations for dynamic scenes that enable view generation with separate control over the camera and the content of the scene.

Chat is not available.