OrthoPlanes: A Novel Representation for Better 3D-Awareness of GANs
We present a new method for generating realistic and view-consistent images with fine
geometry from 2D image collections. Our method proposes a hybrid explicit-implicit …
geometry from 2D image collections. Our method proposes a hybrid explicit-implicit …
Efficient 3d articulated human generation with layered surface volumes
Access to high-quality and diverse 3D articulated digital human assets is crucial in various
applications, ranging from virtual reality to social platforms. Generative approaches, such as …
applications, ranging from virtual reality to social platforms. Generative approaches, such as …
Vive3d: Viewpoint-independent video editing using 3d-aware gans
We introduce VIVE3D, a novel approach that extends the capabilities of image-based 3D
GANs to video editing and is able to represent the input video in an identity-preserving and …
GANs to video editing and is able to represent the input video in an identity-preserving and …
What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs
A Trevithick, M Chan, T Takikawa… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract 3D-aware Generative Adversarial Networks (GANs) have shown remarkable
progress in learning to generate multi-view-consistent images and 3D geometries of scenes …
progress in learning to generate multi-view-consistent images and 3D geometries of scenes …
NeRF-GAN distillation for efficient 3D-aware generation with convolutions
Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent
image generation from single-view datasets, due to their lack of sufficient 3D priors …
image generation from single-view datasets, due to their lack of sufficient 3D priors …
Image captioning based on scene graphs: a survey
J Jia, X Ding, S Pang, X Gao, X Xin, R Hu… - Expert Systems with …, 2023 - Elsevier
Although recent developments in deep learning have brought several tasks closer to human
performance, there is still a significant gap between human and machine performance in …
performance, there is still a significant gap between human and machine performance in …
Learning detailed radiance manifolds for high-fidelity and 3d-consistent portrait synthesis from monocular image
A key challenge for novel view synthesis of monocular portrait images is 3D consistency
under continuous pose variations. Most existing methods rely on 2D generative models …
under continuous pose variations. Most existing methods rely on 2D generative models …
Learning Modulated Transformation in GANs
The success of style-based generators largely benefits from style modulation, which helps
take care of the cross-instance variation within data. However, theinstance-wise stochasticity …
take care of the cross-instance variation within data. However, theinstance-wise stochasticity …
StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer
S Khwanmuang, P Phongthawee… - Proceedings of the …, 2023 - openaccess.thecvf.com
Our paper seeks to transfer the hairstyle of a reference image to an input photo for virtual
hair try-on. We target a variety of challenges scenarios, such as transforming a long hairstyle …
hair try-on. We target a variety of challenges scenarios, such as transforming a long hairstyle …
Mimic3d: Thriving 3d-aware gans via 3d-to-2d imitation
Generating images with both photorealism and multiview 3D consistency is crucial for 3D-
aware GANs, yet existing methods struggle to achieve them simultaneously. Improving the …
aware GANs, yet existing methods struggle to achieve them simultaneously. Improving the …