Generated Contents Enrichment

Hugging Face Daily Papers Papers

Summary

This paper proposes a joint adversarial framework that uses graph convolutional networks to enrich sparse scene graphs before generating semantically richer visual content. The approach makes scene enrichment explicit at the representation level, producing visually plausible and structurally coherent images.

We study Generated Contents Enrichment (GCE), a conditional image-generation task in which a sparse scene description is first enriched through an explicit scene representation and then rendered into semantically richer visual content. Conventional image-generation systems can produce visually realistic outputs from limited scene descriptions, but the added content is usually implicit in the generator rather than represented as an inspectable intermediate structure. In contrast, GCE seeks to make scene enrichment explicit at the scene-representation level while examining its visual consequences during generation, with the goal of encouraging generated content that is visually plausible, structurally coherent, and semantically richer than the sparse input. To instantiate GCE, we propose a jointly trained adversarial framework that enriches scene graphs by modeling object semantics and inter-object relations. Our approach first represents the input description as a scene graph, where nodes model objects and edges capture inter-object relations. The framework uses graph convolutional networks to predict additional objects and their relations to the existing scene. Finally, the enriched scene graph is passed through the downstream image-generation pipeline to generate the corresponding visual content. We evaluate the framework with proxy scene graph enrichment metrics, image-quality comparisons, qualitative examples, and user studies on the Visual Genome dataset.
Original Article
View Cached Full Text

Cached at: 07/06/26, 06:38 PM

Paper page - Generated Contents Enrichment

Source: https://huggingface.co/papers/2405.03650

Abstract

A joint adversarial framework enriches scene graphs using graph convolutional networks to generate semantically richer visual content from sparse scene descriptions.

We study Generated Contents Enrichment (GCE), a conditional image-generation task in which a sparse scene description is first enriched through an explicitscene representationand then rendered into semantically richer visual content. Conventional image-generation systems can produce visually realistic outputs from limited scene descriptions, but the added content is usually implicit in the generator rather than represented as an inspectable intermediate structure. In contrast, GCE seeks to make scene enrichment explicit at the scene-representation level while examining its visual consequences during generation, with the goal of encouraging generated content that is visually plausible, structurally coherent, and semantically richer than the sparse input. To instantiate GCE, we propose a jointly trainedadversarial frameworkthat enrichesscene graphs by modeling object semantics and inter-object relations. Our approach first represents the input description as ascene graph, where nodes model objects and edges capture inter-object relations. The framework usesgraph convolutional networksto predict additional objects and their relations to the existing scene. Finally, the enrichedscene graphis passed through the downstreamimage-generation pipelineto generate the corresponding visual content. We evaluate the framework with proxyscene graphenrichment metrics, image-quality comparisons, qualitative examples, and user studies on the Visual Genome dataset.

View arXiv pageView PDFGitHub0Add to collection

Get this paper in your agent:

hf papers read 2405\.03650

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2405.03650 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2405.03650 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2405.03650 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation

arXiv cs.AI

This paper introduces OmniManim, a render-feedback-aware framework for generating educational animations from natural language descriptions using large language models. It addresses visual defects like element overlap and misalignment by incorporating explicit visual planning, post-render diagnostics, and localized repair, demonstrating improved render quality on newly constructed datasets.