Scene Generation

26 papers with code • 4 benchmarks • 4 datasets

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

Latest papers without code

Semantically Controllable Scene Generation with Guidance of Explicit Knowledge

no code yet • 8 Jun 2021

Deep Generative Models (DGMs) are known for their superior capability in generating realistic data.

Scene Generation

Exploiting Relationship for Complex-scene Image Generation

no code yet • 1 Apr 2021

Our method tends to synthesize plausible layouts and objects, respecting the interplay of multiple objects in an image.

Image Generation Scene Generation

RetrievalFuse: Neural 3D Scene Reconstruction with a Database

no code yet • 31 Mar 2021

3D reconstruction of large scenes is a challenging problem due to the high-complexity nature of the solution space, in particular for generative neural networks.

3D Reconstruction 3D Scene Reconstruction +2

Static and Animated 3D Scene Generation from Free-form Text Descriptions

no code yet • 4 Oct 2020

As the choice of words and syntax vary while preparing a textual description, it is challenging for the system to reliably produce a consistently desirable output from different forms of language input.

Language Modelling Scene Generation

SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans

no code yet • CVPR 2021

We present SPSG, a novel approach to generate high-quality, colored 3D models of scenes from RGB-D scan observations by learning to infer unobserved scene geometry and color in a self-supervised fashion.

3D Reconstruction Scene Generation

ROOTS: Object-Centric Representation and Rendering of 3D Scenes

no code yet • 11 Jun 2020

A crucial ability of human intelligence is to build up models of individual 3D objects from partial scene observations.

Representation Learning Scene Generation

LayoutVAE: Stochastic Scene Layout Generation From a Label Set

no code yet • ICCV 2019

Recently there is an increasing interest in scene generation within the research community.

Scene Generation

COCO-GAN: Conditional Coordinate Generative Adversarial Network

no code yet • ICLR 2019

The fact that the patch generation process is independent to each other inspires a wide range of new applications: firstly, "Patch-Inspired Image Generation" enables us to generate the entire image based on a single patch.

Image Generation Scene Generation

UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition

no code yet • 18 Apr 2018

This paper studies how weight repetition ---when the same weight occurs multiple times in or across weight vectors--- can be exploited to save energy and improve performance during CNN inference.

Scene Generation

Depth Structure Preserving Scene Image Generation

no code yet • 1 Jun 2017

Key to automatically generate natural scene images is to properly arrange among various spatial elements, especially in the depth direction.

Image Generation Scene Generation