SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.05957 · 2023

DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
taldatech/ddlp canonical 4 of 5
FunctionStatusWhere it lives
identity Ran taldatech/ddlp/modules/diffusion_modules.py
code served (permissive licence) · get_code("7f1040f5e3991d5e")
conv1x1 Ran taldatech/ddlp/modules/modules.py
code served (permissive licence) · get_code("d9def42110729a85")
default Ran taldatech/ddlp/modules/diffusion_modules.py
code served (permissive licence) · get_code("d1ef6b8cb9a28a53")
exists Ran taldatech/ddlp/modules/diffusion_modules.py
code served (permissive licence) · get_code("608e364a9d2376a3")
conv3x3 Not yet run taldatech/ddlp/modules/modules.py
code served (permissive licence) · get_code("00be6a9dc697991e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a new object-centric video prediction algorithm based on the deep latent particle (DLP) representation. In comparison to existing slot- or patch-based representations, DLPs model the scene using a set of keypoints with learned parameters for properties such as position and size, and are both efficient and interpretable. Our method, deep dynamic latent particles (DDLP), yields state-of-the-art object-centric video prediction results on several challenging datasets. The interpretable nature of DDLP allows us to perform ``what-if'' generation -- predict the consequence of changing properties of objects in the initial frames, and DLP's compact structure enables efficient diffusion-based unconditional video generation. Videos, code and pre-trained models are available: https://taldatech.github.io/ddlp-web

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2306.05957")
get_code_for_paper("2306.05957")
have("2306.05957")

Connect an agent — have() is free.