image-generation

Image Generation from Scene Graphs

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in image-generation

Trend

Dataset

Best Model

Actions

BDD100K-Subsets

Visual Genome 64x64

Home Action Genome

Libraries

i

Use these libraries to find image-generation models and implementations

Datasets

Visual Genome

Home Action Genome

BDD100K-Subsets

Subtasks

No subtasks available.

Most implemented papers

Image Generation from Scene Graphs

Justin Johnson, Li Fei-Fei, Agrim Gupta•Tue Apr 03 2018

This work proposes a method for generating images from scene graphs, enabling explicitly reasoning about objects and their relationships, and validates this approach on Visual Genome and COCO-Stuff.

887

Content

Home Action Genome

0

Paper Graph

MIGS: Meta Image Generation from Scene Graphs

Nassir Navab, Helisa Dhamo, Azade Farshad, S. Musatian•Thu Oct 21 2021

This work proposes MIGS (Meta Image Generation from Scene Graphs), a meta-learning based approach for few-shot image generation from graphs that enables adapting the model to different scenes and increases the image quality by training on diverse sets of tasks.

10 0

Paper Graph

Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation

Maelic Neau, Paulo E. Santos, Anne-Gwenn Bosser, Cédric Buche•Mon May 29 2023

A new dataset, VG150-curated, based on the annotations of the popular Visual Genome dataset is presented, showing through a set of experiments that this dataset contains more high-quality and diverse annotations than the one usually use in SGG.

5 0

Paper Graph

Transformer-based Image Generation from Scene Graphs

S. Palazzo, C. Spampinato, R. Sortino•Tue Mar 07 2023

This work shows how employing multi-head attention to encode the graph information, as well as using a transformer-based model in the latent space for image generation can improve the quality of the sampled data, without the need to employ adversarial models with the subsequent advantage in terms of training stability.

18 0

Paper Graph

Adding a benchmark result helps the community track progress.