227 citations · 551 across the 25 of their papers we have counts for
26 papers
HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
Tong Wu, Zhibing Li, Shuai Yang +5
3D content creation from a single image is a long-standing yet highly desirable task. Recent advances introduce 2D diffusion priors, yielding reasonable results. However, existing…
MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR
Xudong Xu, Zhaoyang Lyu, Xingang Pan +1
Based on powerful text-to-image diffusion models, text-to-3D generation has made significant progress in generating compelling geometry and appearance. However, existing methods st…
AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars
Mohit Mendiratta, Xingang Pan, Mohamed Elgharib +6
Capturing and editing full head performances enables the creation of virtual characters with various applications such as extended reality and media production. The past few years…
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Xingang Pan, Ayush Tewari, Thomas Leimkühler +3
Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. Existin…
GVP: Generative Volumetric Primitives
Mallikarjun B R, Xingang Pan, Mohamed Elgharib +1
Advances in 3D-aware generative models have pushed the boundary of image synthesis with explicit camera control. To achieve high-resolution image synthesis, several attempts have b…
HQ3DAvatar: High Quality Controllable 3D Head Avatar
Kartik Teotia, Mallikarjun B R, Xingang Pan +4
Multi-view volumetric rendering techniques have recently shown great potential in modeling and synthesizing high-quality head avatars. A common approach to capture full head dynami…
Grid-guided Neural Radiance Fields for Large Urban Scenes
Linning Xu, Yuanbo Xiangli, Sida Peng +5
Purely MLP-based neural radiance fields (NeRF-based methods) often suffer from underfitting with blurred renderings on large-scale scenes due to limited model capacity. Recent appr…
AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation
Yuanbo Xiangli, Linning Xu, Xingang Pan +3
Both indoor and outdoor environments are inherently structured and repetitive. Traditional modeling pipelines keep an asset library storing unique object templates, which is both v…
GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild
Chao Wang, Ana Serrano, Xingang Pan +5
Most in-the-wild images are stored in Low Dynamic Range (LDR) form, serving as a partial observation of the High Dynamic Range (HDR) visual world. Despite limited dynamic range, th…
gCoRF: Generative Compositional Radiance Fields
Mallikarjun BR, Ayush Tewari, Xingang Pan +2
3D generative models of objects enable photorealistic image synthesis with 3D control. Existing methods model the scene as a global scene representation, ignoring the compositional…
Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
Tong Wu, Jiaqi Wang, Xingang Pan +4
Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit m…
GAN2X: Non-Lambertian Inverse Rendering of Image GANs
Xingang Pan, Ayush Tewari, Lingjie Liu +1
2D images are observations of the 3D physical world depicted with the geometry, material, and illumination components. Recovering these underlying intrinsic components from 2D imag…
Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
Ayush Tewari, Mallikarjun B R, Xingang Pan +3
Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs whi…
BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
Yuanbo Xiangli, Linning Xu, Xingang Pan +5
Neural radiance fields (NeRF) has achieved outstanding performance in modeling 3D objects and controlled scenes, usually under a single scale. In this work, we focus on multi-scale…
Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
Xudong Xu, Xingang Pan, Dahua Lin +1
The advent of generative radiance fields has significantly promoted the development of 3D-aware image synthesis. The cumulative rendering process in radiance fields makes training…
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
Xingang Pan, Xudong Xu, Chen Change Loy +2
The advancement of generative radiance fields has pushed the boundary of 3D-aware image synthesis. Motivated by the observation that a 3D object should look realistic from multiple…
Talk-to-Edit: Fine-Grained Facial Editing via Dialog
Yuming Jiang, Ziqi Huang, Xingang Pan +2
Facial editing is an important task in vision and graphics with numerous applications. However, existing works are incapable to deliver a continuous and fine-grained editing mode (…
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Xingang Pan, Bo Dai, Ziwei Liu +2
Natural images are projections of 3D objects on a 2D image plane. While state-of-the-art 2D generative models like GANs show unprecedented quality in modeling the natural image man…
Self-Supervised Scene De-occlusion
Xiaohang Zhan, Xingang Pan, Bo Dai +3
Natural scene understanding is a challenging task, particularly when encountering images of multiple objects that are partially occluded. This obstacle is given rise by varying obj…
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Xingang Pan, Xiaohang Zhan, Bo Dai +3
Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there…
Channel Equilibrium Networks for Learning Deep Representation
Wenqi Shao, Shitao Tang, Xingang Pan +3
Convolutional Neural Networks (CNNs) are typically constructed by stacking multiple building blocks, each of which contains a normalization layer such as batch normalization (BN) a…
Open Compound Domain Adaptation
Ziwei Liu, Zhongqi Miao, Xingang Pan +4
A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e.g., sunny weather) for achieving high performance on the test data in a…
Self-Supervised Learning via Conditional Motion Propagation
Xiaohang Zhan, Xingang Pan, Ziwei Liu +2
Intelligent agent naturally learns from motion. Various self-supervised algorithms have leveraged motion cues to learn effective visual representations. The hurdle here is that mot…
Switchable Whitening for Deep Representation Learning
Xingang Pan, Xiaohang Zhan, Jianping Shi +2
Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixe…