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 …

Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation

R Chen, Y Chen, N Jiao, K Jia - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Automatic 3D content creation has achieved rapid progress recently due to the availability of
pre-trained, large language models and image diffusion models, forming the emerging topic …

Mvdream: Multi-view diffusion for 3d generation

Y Shi, P Wang, J Ye, M Long, K Li, X Yang - arXiv preprint arXiv …, 2023 - arxiv.org
We propose MVDream, a multi-view diffusion model that is able to generate geometrically
consistent multi-view images from a given text prompt. By leveraging image diffusion models …

Generative novel view synthesis with 3d-aware diffusion models

ER Chan, K Nagano, MA Chan… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present a diffusion-based model for 3D-aware generative novel view synthesis from as
few as a single input image. Our model samples from the distribution of possible renderings …

Nerfdiff: Single-image view synthesis with nerf-guided distillation from 3d-aware diffusion

J Gu, A Trevithick, KE Lin, JM Susskind… - International …, 2023 - proceedings.mlr.press
Novel view synthesis from a single image requires inferring occluded regions of objects and
scenes whilst simultaneously maintaining semantic and physical consistency with the input …

Align your gaussians: Text-to-4d with dynamic 3d gaussians and composed diffusion models

H Ling, SW Kim, A Torralba… - Proceedings of the …, 2024 - openaccess.thecvf.com
Text-guided diffusion models have revolutionized image and video generation and have
also been successfully used for optimization-based 3D object synthesis. Here we instead …

Tri-miprf: Tri-mip representation for efficient anti-aliasing neural radiance fields

W Hu, Y Wang, L Ma, B Yang, L Gao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Despite the tremendous progress in neural radiance fields (NeRF), we still face a dilemma of
the trade-off between quality and efficiency, eg, MipNeRF presents fine-detailed and anti …

Single-stage diffusion nerf: A unified approach to 3d generation and reconstruction

H Chen, J Gu, A Chen, W Tian, Z Tu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract 3D-aware image synthesis encompasses a variety of tasks, such as scene
generation and novel view synthesis from images. Despite numerous task-specific methods …

A survey on generative diffusion models

H Cao, C Tan, Z Gao, Y Xu, G Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep generative models have unlocked another profound realm of human creativity. By
capturing and generalizing patterns within data, we have entered the epoch of all …

Analyzing and improving the training dynamics of diffusion models

T Karras, M Aittala, J Lehtinen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Diffusion models currently dominate the field of data-driven image synthesis with their
unparalleled scaling to large datasets. In this paper we identify and rectify several causes for …