Papers › GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

30 Jul 2019ICLR 2020 1arXiv:1907.13052archive 2025-07-28

Martin Engelcke, Adam R. Kosiorek, Oiwi Parker Jones, Ingmar Posner

Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet and IODINE, decompose scenes into objects in an unsupervised fashion. Their underlying generative processes, however, do not account for component interactions. Hence, neither of them allows for principled sampling of novel scenes. Here we present GENESIS, the first object-centric generative model of 3D visual scenes capable of both decomposing and generating scenes by capturing relationships between scene components. GENESIS parameterises a spatial GMM over images which is decoded from a set of object-centric latent variables that are either inferred sequentially in an amortised fashion or sampled from an autoregressive prior. We train GENESIS on several publicly available datasets and evaluate its performance on scene generation, decomposition, and semi-supervised learning.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

applied-ai-lab/genesis officialmentioned in papermentioned on GitHubpytorchGPL-3.0 report
jinyangyuan/genesis mentioned on GitHubpytorchGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image GenerationObject DiscoveryReinforcement LearningRepresentation LearningScene GenerationUnsupervised Image SegmentationUnsupervised Object Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation GQN GENESIS FID 80.5 #1 of 1 Archive leaderboard report
Image Generation Multi-dSprites GENESIS FID 24.9 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamBatch NormalizationELUGECOGated Linear UnitLSTMMoNetSigmoid ActivationSpatial Broadcast DecoderTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections