95 citations · 525 across the 28 of their papers we have counts for
23 papers · 1 filter
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Jingxiang Sun, Bo Zhang, Ruizhi Shao +4
We present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image t…
Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
Junshu Tang, Tengfei Wang, Bo Zhang +4
In this work, we investigate the problem of creating high-fidelity 3D content from only a single image. This is inherently challenging: it essentially involves estimating the under…
Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion
Tengfei Wang, Bo Zhang, Ting Zhang +8
This paper presents a 3D generative model that uses diffusion models to automatically generate 3D digital avatars represented as neural radiance fields. A significant challenge in…
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
Bowen Zhang, Chenyang Qi, Pan Zhang +6
In this work, we propose an ID-preserving talking head generation framework, which advances previous methods in two aspects. First, as opposed to interpolating from sparse flow, we…
Paint by Example: Exemplar-based Image Editing with Diffusion Models
Binxin Yang, Shuyang Gu, Bo Zhang +5
Language-guided image editing has achieved great success recently. In this paper, for the first time, we investigate exemplar-guided image editing for more precise control. We achi…
3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation
Junshu Tang, Bo Zhang, Binxin Yang +4
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While p…
Pretraining is All You Need for Image-to-Image Translation
Tengfei Wang, Ting Zhang, Bo Zhang +4
We propose to use pretraining to boost general image-to-image translation. Prior image-to-image translation methods usually need dedicated architectural design and train individual…
Real-Time Neural Character Rendering with Pose-Guided Multiplane Images
Hao Ouyang, Bo Zhang, Pan Zhang +5
We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality. We use a portable camera rig to capture…
Bringing Old Films Back to Life
Ziyu Wan, Bo Zhang, Dongdong Chen +1
We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films. Instead of performing frame-wise restoration, our method is based…
StyleSwin: Transformer-based GAN for High-resolution Image Generation
Bowen Zhang, Shuyang Gu, Bo Zhang +5
Despite the tantalizing success in a broad of vision tasks, transformers have not yet demonstrated on-par ability as ConvNets in high-resolution image generative modeling. In this…
Vector Quantized Diffusion Model for Text-to-Image Synthesis
Shuyang Gu, Dong Chen, Jianmin Bao +5
We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose laten…
Robust Mutual Learning for Semi-supervised Semantic Segmentation
Pan Zhang, Bo Zhang, Ting Zhang +2
Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learnin…
Let's See Clearly: Contaminant Artifact Removal for Moving Cameras
Xiaoyu Li, Bo Zhang, Jing Liao +1
Contaminants such as dust, dirt and moisture adhering to the camera lens can greatly affect the quality and clarity of the resulting image or video. In this paper, we propose a vid…
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
Chulin Xie, Chuxin Wang, Bo Zhang +3
In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion. Firstly, we present the channel-attentive EdgeConv…
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
Pan Zhang, Bo Zhang, Ting Zhang +3
Self-training is a competitive approach in domain adaptive segmentation, which trains the network with the pseudo labels on the target domain. However inevitably, the pseudo labels…
CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
Xingran Zhou, Bo Zhang, Ting Zhang +5
We present the full-resolution correspondence learning for cross-domain images, which aids image translation. We adopt a hierarchical strategy that uses the correspondence from coa…
Old Photo Restoration via Deep Latent Space Translation
Ziyu Wan, Bo Zhang, Dongdong Chen +4
We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised l…
Deep Sketch-guided Cartoon Video Inbetweening
Xiaoyu Li, Bo Zhang, Jing Liao +1
We propose a novel framework to produce cartoon videos by fetching the color information from two input keyframes while following the animated motion guided by a user sketch. The k…
Bringing Old Photos Back to Life
Ziyu Wan, Bo Zhang, Dongdong Chen +4
We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised l…
Cross-domain Correspondence Learning for Exemplar-based Image Translation
Pan Zhang, Bo Zhang, Dong Chen +2
We present a general framework for exemplar-based image translation, which synthesizes a photo-realistic image from the input in a distinct domain (e.g., semantic segmentation mask…
Document Rectification and Illumination Correction using a Patch-based CNN
Xiaoyu Li, Bo Zhang, Jing Liao +1
We propose a novel learning method to rectify document images with various distortion types from a single input image. As opposed to previous learning-based methods, our approach s…
Blind Geometric Distortion Correction on Images Through Deep Learning
Xiaoyu Li, Bo Zhang, Pedro V. Sander +1
We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural ne…
Deep Exemplar-based Video Colorization
Bo Zhang, Mingming He, Jing Liao +4
This paper presents the first end-to-end network for exemplar-based video colorization. The main challenge is to achieve temporal consistency while remaining faithful to the refere…