Gpt-4v (ision) is a human-aligned evaluator for text-to-3d generation

T Wu, G Yang, Z Li, K Zhang, Z Liu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Despite recent advances in text-to-3D generative methods there is a notable absence of
reliable evaluation metrics. Existing metrics usually focus on a single criterion each such as …

Cad: Photorealistic 3d generation via adversarial distillation

Z Wan, D Paschalidou, I Huang, H Liu… - Proceedings of the …, 2024 - openaccess.thecvf.com
The increased demand for 3D data in AR/VR robotics and gaming applications gave rise to
powerful generative pipelines capable of synthesizing high-quality 3D objects. Most of these …

Commonscenes: Generating commonsense 3d indoor scenes with scene graphs

G Zhai, EP Örnek, SC Wu, Y Di… - Advances in …, 2024 - proceedings.neurips.cc
Controllable scene synthesis aims to create interactive environments for various industrial
use cases. Scene graphs provide a highly suitable interface to facilitate these applications …

Controlroom3d: Room generation using semantic proxy rooms

J Schult, S Tsai, L Höllein, B Wu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Manually creating 3D environments for AR/VR applications is a complex process requiring
expert knowledge in 3D modeling software. Pioneering works facilitate this process by …

Berfscene: Bev-conditioned equivariant radiance fields for infinite 3d scene generation

Q Zhang, Y Xu, Y Shen, B Dai… - Proceedings of the …, 2024 - openaccess.thecvf.com
Generating large-scale 3D scenes cannot simply apply existing 3D object synthesis
technique since 3D scenes usually hold complex spatial configurations and consist of a …

Scenewiz3d: Towards text-guided 3d scene composition

Q Zhang, C Wang, A Siarohin, P Zhuang, Y Xu… - arXiv preprint arXiv …, 2023 - arxiv.org
We are witnessing significant breakthroughs in the technology for generating 3D objects
from text. Existing approaches either leverage large text-to-image models to optimize a 3D …

Urbangiraffe: Representing urban scenes as compositional generative neural feature fields

Y Yang, Y Yang, H Guo, R Xiong… - Proceedings of the …, 2023 - openaccess.thecvf.com
Generating photorealistic images with controllable camera pose and scene contents is
essential for many applications including AR/VR and simulation. Despite the fact that rapid …

Roomdreamer: Text-driven 3d indoor scene synthesis with coherent geometry and texture

L Song, L Cao, H Xu, K Kang, F Tang, J Yuan… - arXiv preprint arXiv …, 2023 - arxiv.org
The techniques for 3D indoor scene capturing are widely used, but the meshes produced
leave much to be desired. In this paper, we propose" RoomDreamer", which leverages …

Ctrl-room: Controllable text-to-3d room meshes generation with layout constraints

C Fang, X Hu, K Luo, P Tan - arXiv preprint arXiv:2310.03602, 2023 - arxiv.org
Text-driven 3D indoor scene generation could be useful for gaming, film industry, and
AR/VR applications. However, existing methods cannot faithfully capture the room layout …

Tc4d: Trajectory-conditioned text-to-4d generation

S Bahmani, X Liu, Y Wang, I Skorokhodov… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent techniques for text-to-4D generation synthesize dynamic 3D scenes using
supervision from pre-trained text-to-video models. However, existing representations for …