Consistent view synthesis with pose-guided diffusion models
Novel view synthesis from a single image has been a cornerstone problem for many Virtual
Reality applications that provide immersive experiences. However, most existing techniques …
Reality applications that provide immersive experiences. However, most existing techniques …
Stylizednerf: consistent 3d scene stylization as stylized nerf via 2d-3d mutual learning
Abstract 3D scene stylization aims at generating stylized images of the scene from arbitrary
novel views following a given set of style examples, while ensuring consistency when …
novel views following a given set of style examples, while ensuring consistency when …
Space-time neural irradiance fields for free-viewpoint video
We present a method that learns a spatiotemporal neural irradiance field for dynamic scenes
from a single video. Our learned representation enables free-viewpoint rendering of the …
from a single video. Our learned representation enables free-viewpoint rendering of the …
Intelligent layout generation based on deep generative models: A comprehensive survey
Y Shi, M Shang, Z Qi - Information Fusion, 2023 - Elsevier
Layout generation, as a crucial stage in Artificial Intelligence-Generated Content (AIGC) task
information presentation generation, is a fascinating and significant research topic …
information presentation generation, is a fascinating and significant research topic …
Regularizing generative adversarial networks under limited data
Recent years have witnessed the rapid progress of generative adversarial networks (GANs).
However, the success of the GAN models hinges on a large amount of training data. This …
However, the success of the GAN models hinges on a large amount of training data. This …
3d-aware conditional image synthesis
We propose pix2pix3D, a 3D-aware conditional generative model for controllable
photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map …
photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map …
Efficient semantic image synthesis via class-adaptive normalization
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional
semantic image synthesis in T. Park et al. 2019 which modulates the normalized activation …
semantic image synthesis in T. Park et al. 2019 which modulates the normalized activation …
Neural deformable voxel grid for fast optimization of dynamic view synthesis
Abstract Recently, Neural Radiance Fields (NeRF) is revolutionizing the task of novel view
synthesis (NVS) for its superior performance. In this paper, we propose to synthesize …
synthesis (NVS) for its superior performance. In this paper, we propose to synthesize …
Learning to stylize novel views
We tackle a 3D scene stylization problem--generating stylized images of a scene from
arbitrary novel views given a set of images of the same scene and a reference image of the …
arbitrary novel views given a set of images of the same scene and a reference image of the …
Upst-nerf: Universal photorealistic style transfer of neural radiance fields for 3d scene
Y Chen, Q Yuan, Z Li, Y Liu, W Wang… - … on Visualization and …, 2024 - ieeexplore.ieee.org
Photorealistic stylization of 3D scenes aims to generate photorealistic images from arbitrary
novel views according to a given style image, while ensuring consistency when rendering …
novel views according to a given style image, while ensuring consistency when rendering …