Based on powerful text-to-image diffusion models, text-to-3D generation ...
Capturing and editing full head performances enables the creation of vir...
Synthesizing visual content that meets users' needs often requires flexi...
Advances in 3D-aware generative models have pushed the boundary of image...
Multi-view volumetric rendering techniques have recently shown great
pot...
Purely MLP-based neural radiance fields (NeRF-based methods) often suffe...
Both indoor and outdoor environments are inherently structured and
repet...
3D generative models of objects enable photorealistic image synthesis wi...
Neural surface reconstruction aims to reconstruct accurate 3D surfaces b...
2D images are observations of the 3D physical world depicted with the
ge...
Learning 3D generative models from a dataset of monocular images enables...
Neural Radiance Field (NeRF) has achieved outstanding performance in mod...
The advent of generative radiance fields has significantly promoted the
...
The advancement of generative radiance fields has pushed the boundary of...
Facial editing is an important task in vision and graphics with numerous...
Natural images are projections of 3D objects on a 2D image plane. While
...
Natural scene understanding is a challenging task, particularly when
enc...
Learning a good image prior is a long-term goal for image restoration an...
Convolutional Neural Networks (CNNs) are typically constructed by stacki...
Existing works on domain adaptation often assume clear boundaries betwee...
Normalization methods are essential components in convolutional neural
n...
Intelligent agent naturally learns from motion. Various self-supervised
...
Convolutional neural networks (CNNs) have achieved great successes in ma...
Convolutional neural networks (CNNs) are usually built by stacking
convo...