Generative Adversarial Transformers

[arXiv'24] [Image-to-Scene on a 4090(24G)] VistaDream: Sampling multiview consistent images for single-view scene reconstruction

Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”

[CVPR 2024] DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis

[3DV 2021 Oral] Sceneformer: Indoor Scene Generation with Transformers: Generate indoor scenes with Transformers

We introduce LT3SD, a novel latent 3D scene diffusion approach enabling high-fidelity generation of infinite 3D environments in a patch-by-patch and coarse-to-fine fashion.

Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

[NeurIPS 2023] The repo of CommonScenes, a scene generation method powered by the diffusion model.

[CVPR2024] DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation

[ECCV 2024] EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion.

Official code for "End-to-End Optimization of Scene Layout" -- including VAE, Diff Render, SPADE for colorization (CVPR 2020 Oral)

[AAAI 2019] A Layer-Based Sequential Framework for Scene Generation with GANs

Code for "Probabilistic Neural Programmed Networks for Scene Generation.", Deng et al, NIPS 2018

[ECCV24] Official code for RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting

[3DV 2024] official repo of 3DV paper "RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation"

[ICRA 2024] SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs

GenWorld - a procedural generation toolkit for the "Unity" game engine. Allows you to procedurally generate content for a scene from voxels. Uses various algorithms and methods where you can change the frequency of appearance, size and color of voxel models.

Scene generation from novel viewpoints - Graph element networks

Project Page for [MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation]

Leveraging various traditional and modern NLP approaches to analyse a dataset with script lines from the US TV-show "The Office".