State of the art on diffusion models for visual computing

R Po, W Yifan, V Golyanik, K Aberman… - Computer Graphics …, 2024 - Wiley Online Library
The field of visual computing is rapidly advancing due to the emergence of generative
artificial intelligence (AI), which unlocks unprecedented capabilities for the generation …

Magic3d: High-resolution text-to-3d content creation

CH Lin, J Gao, L Tang, T Takikawa… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recently, DreamFusion demonstrated the utility of a pretrained text-to-image diffusion model
to optimize Neural Radiance Fields (NeRF), achieving remarkable text-to-3D synthesis …

One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization

M Liu, C Xu, H Jin, L Chen… - Advances in Neural …, 2024 - proceedings.neurips.cc
Single image 3D reconstruction is an important but challenging task that requires extensive
knowledge of our natural world. Many existing methods solve this problem by optimizing a …

Latent-nerf for shape-guided generation of 3d shapes and textures

G Metzer, E Richardson, O Patashnik… - Proceedings of the …, 2023 - openaccess.thecvf.com
Text-guided image generation has progressed rapidly in recent years, inspiring major
breakthroughs in text-guided shape generation. Recently, it has been shown that using …

Lion: Latent point diffusion models for 3d shape generation

A Vahdat, F Williams, Z Gojcic… - Advances in …, 2022 - proceedings.neurips.cc
Denoising diffusion models (DDMs) have shown promising results in 3D point cloud
synthesis. To advance 3D DDMs and make them useful for digital artists, we require (i) high …

Shap-e: Generating conditional 3d implicit functions

H Jun, A Nichol - arXiv preprint arXiv:2305.02463, 2023 - arxiv.org
We present Shap-E, a conditional generative model for 3D assets. Unlike recent work on 3D
generative models which produce a single output representation, Shap-E directly generates …

Text-to-3d using gaussian splatting

Z Chen, F Wang, Y Wang, H Liu - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Automatic text-to-3D generation that combines Score Distillation Sampling (SDS) with the
optimization of volume rendering has achieved remarkable progress in synthesizing realistic …

One-2-3-45++: Fast single image to 3d objects with consistent multi-view generation and 3d diffusion

M Liu, R Shi, L Chen, Z Zhang, C Xu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recent advancements in open-world 3D object generation have been remarkable with
image-to-3D methods offering superior fine-grained control over their text-to-3D …

Multimodal learning with transformers: A survey

P Xu, X Zhu, DA Clifton - IEEE Transactions on Pattern Analysis …, 2023 - ieeexplore.ieee.org
Transformer is a promising neural network learner, and has achieved great success in
various machine learning tasks. Thanks to the recent prevalence of multimodal applications …

Dream3d: Zero-shot text-to-3d synthesis using 3d shape prior and text-to-image diffusion models

J Xu, X Wang, W Cheng, YP Cao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recent CLIP-guided 3D optimization methods, such as DreamFields and PureCLIPNeRF,
have achieved impressive results in zero-shot text-to-3D synthesis. However, due to scratch …