Search Results for author:
Found 72 papers, 45 papers with code
FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content
In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input.
DCT-Net: Domain-Calibrated Translation for Portrait Stylization
This paper introduces DCT-Net, a novel image translation architecture for few-shot portrait stylization.
AnyText: Multilingual Visual Text Generation And Editing
Based on AnyWord-3M dataset, we propose AnyText-benchmark for the evaluation of visual text generation accuracy and quality.
GAN Prior Embedded Network for Blind Face Restoration in the Wild
The proposed GAN prior embedded network (GPEN) is easy-to-implement, and it can generate visually photo-realistic results.
Ranked #1 on
Blind Face Restoration
on CelebA-HQ
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization
Diffusion models have demonstrated impressive performance in various image generation, editing, enhancement and translation tasks.
DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders
Image colorization is a challenging problem due to multi-modal uncertainty and high ill-posedness.
Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters
With DIAL-Filters, we design both unsupervised and supervised frameworks for nighttime driving-scene segmentation, which can be trained in an end-to-end manner.
Boosting Semantic Human Matting with Coarse Annotations
In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input.
Ranked #9 on
Image Matting
on AM-2K
A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images
Meanwhile, 3D priors of facial details are incorporated to enhance the accuracy and authenticity of the reconstruction results.
Ranked #3 on
3D Face Reconstruction
on REALY (side-view)
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
To solve this problem, we propose \textbf{InfoBatch}, a novel framework aiming to achieve lossless training acceleration by unbiased dynamic data pruning.
PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency
HRP requires that more attention should be paid to human regions, while GLC requires that a group of portrait photos should be retouched to a consistent tone.
GMLight: Lighting Estimation via Geometric Distribution Approximation
This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation.
FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation
In this paper, we show the strong potential of query-based models on efficient instance segmentation algorithm designs.
Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models
This is a technical report on the 360-degree panoramic image generation task based on diffusion models.
DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation
Text-to-3D generation, which synthesizes 3D assets according to an overall text description, has significantly progressed.
Structure-Aware Flow Generation for Human Body Reshaping
Body reshaping is an important procedure in portrait photo retouching.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models
Different from conventional T2V sampling (i. e., temporal and spatial modeling), VideoElevator explicitly decomposes each sampling step into temporal motion refining and spatial quality elevating.
Attention-aware Multi-stroke Style Transfer
Neural style transfer has drawn considerable attention from both academic and industrial field.
Attention-guided Temporally Coherent Video Object Matting
Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.
Active Boundary Loss for Semantic Segmentation
This paper proposes a novel active boundary loss for semantic segmentation.
Hypergraph Transformer for Skeleton-based Action Recognition
Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections.
Ranked #7 on
Skeleton Based Action Recognition
on NTU RGB+D 120
ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo
The network is mainly composed of two components: a context-aware local retouching layer (LRL) and an adaptive blend pyramid layer (BPL).
WaveFill: A Wavelet-based Generation Network for Image Inpainting
This paper presents WaveFill, a wavelet-based inpainting network that decomposes images into multiple frequency bands and fills the missing regions in each frequency band separately and explicitly.
Tracking with Human-Intent Reasoning
The perception component then generates the tracking results based on the embeddings.
SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions
The key idea of our SmartControl is to relax the visual condition on the areas that are conflicted with text prompts.
Towards Counterfactual Image Manipulation via CLIP
In addition, we design a simple yet effective scheme that explicitly maps CLIP embeddings (of target text) to the latent space and fuses them with latent codes for effective latent code optimization and accurate editing.
Noise-resistant Deep Metric Learning with Ranking-based Instance Selection
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models.
TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective
We investigate the reasons for this phenomenon and discover that the existing data augmentation approach and hard sample mining strategy are incompatible with ViTs-based FR backbone due to the lack of tailored consideration on preserving face structural information and leveraging each local token information.
HDFormer: High-order Directed Transformer for 3D Human Pose Estimation
Human pose estimation is a challenging task due to its structured data sequence nature.
Ranked #74 on
3D Human Pose Estimation
on Human3.6M
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
As a remedy, we propose a threefold strategy: (1) We forge an innovative pathway that encodes bone connectivity by harnessing the power of graph distances.
RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters
Therefore, there is a need for white-box approaches that produce satisfying results and enable users to conveniently edit their images simultaneously.
Ranked #3 on
Image Enhancement
on MIT-Adobe 5k
(PSNR on proRGB metric)
Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition
Most of the existing deep learning based VFI methods adopt off-the-shelf optical flow algorithms to estimate the bidirectional flows and interpolate the missing frames accordingly.
ProContEXT: Exploring Progressive Context Transformer for Tracking
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template.
PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation
Typically, PoSynDA uses a diffusion-inspired structure to simulate 3D pose distribution in the target domain.
Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets.
LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception
Streaming perception is a critical task in autonomous driving that requires balancing the latency and accuracy of the autopilot system.
Region-adaptive Texture Enhancement for Detailed Person Image Synthesis
The ability to produce convincing textural details is essential for the fidelity of synthesized person images.
Ranked #4 on
Pose Transfer
on Deep-Fashion
KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration
By spearheading the integration of Multilateration with facial analysis, KeyPosS marks a paradigm shift in facial landmark detection.
Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation
Accurately estimating the 3D pose of humans in video sequences requires both accuracy and a well-structured architecture.
DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving
Real-time perception, or streaming perception, is a crucial aspect of autonomous driving that has yet to be thoroughly explored in existing research.
PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering
Semantic segmentation of point clouds usually requires exhausting efforts of human annotations, hence it attracts wide attention to the challenging topic of learning from unlabeled or weaker forms of annotations.
PointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-Modal Distillation and Super-Voxel Clustering
Semantic segmentation of point clouds usually requires exhausting efforts of human annotations, hence it attracts wide attention to a challenging topic of learning from unlabeled or weaker form of annotations.
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier
The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
Ranked #3 on
Universal Domain Adaptation
on Office-31
Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks
The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0. 947 $\pm$ 0. 044.
Generating Persuasive Visual Storylines for Promotional Videos
Video contents have become a critical tool for promoting products in E-commerce.
A Multi-Task Learning Framework for Extracting Bacteria Biotope Information
This paper presents a novel transfer multi-task learning method for Bacteria Biotope rel+ner task at BioNLP-OST 2019.
Towards Realistic 3D Embedding via View Alignment
Recent advances in generative adversarial networks (GANs) have achieved great success in automated image composition that generates new images by embedding interested foreground objects into background images automatically.
Adversarial Image Composition with Auxiliary Illumination
State-of-the-art methods strive to harmonize the composed image by adapting the style of foreground objects to be compatible with the background image, whereas the potential shadow of foreground objects within the composed image which is critical to the composition realism is largely neglected.
EMLight: Lighting Estimation via Spherical Distribution Approximation
Motivated by the Earth Mover distance, we design a novel spherical mover's loss that guides to regress light distribution parameters accurately by taking advantage of the subtleties of spherical distribution.
Diverse Image Inpainting with Bidirectional and Autoregressive Transformers
With image-level attention, transformers enable to model long-range dependencies and generate diverse contents with autoregressive modeling of pixel-sequence distributions.
Unbalanced Feature Transport for Exemplar-based Image Translation
In addition, we design a semantic-activation normalization scheme that injects style features of exemplars into the image translation process successfully.
Sparse Needlets for Lighting Estimation with Spherical Transport Loss
Accurate lighting estimation is challenging yet critical to many computer vision and computer graphics tasks such as high-dynamic-range (HDR) relighting.
Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering
Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks.
Unpaired Cartoon Image Synthesis via Gated Cycle Mapping
Experimental results demonstrate the superiority of the proposed method over the state of the art and validate its effectiveness in the brand-new task of general cartoon image synthesis.
Semi-supervised Deep Multi-view Stereo
For further troublesome case that the basic assumption is conflicted in MVS data, we propose a novel style consistency loss to alleviate the negative effect caused by the distribution gap.
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier
The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
Improving Training and Inference of Face Recognition Models via Random Temperature Scaling
Intuitively, FR algorithms can benefit from both the estimation of uncertainty and the detection of out-of-distribution (OOD) samples.
Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approach
In supervised image restoration tasks, one key issue is how to obtain the aligned high-quality (HQ) and low-quality (LQ) training image pairs.
Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection
End-to-end pedestrian detection focuses on training a pedestrian detection model via discarding the Non-Maximum Suppression (NMS) post-processing.
CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo
The Residual Depth-Aware Cost Transformer(RDACT) is proposed to aggregate long-range features on cost volume via self-attention mechanisms along the depth and spatial dimensions.
WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models
This paper introduces WordArt Designer, a user-driven framework for artistic typography synthesis, relying on the Large Language Model (LLM).
FMViT: A multiple-frequency mixing Vision Transformer
On CoreML, FMViT outperforms MobileOne by 2. 6% in top-1 accuracy on the ImageNet dataset, with inference latency comparable to MobileOne (78. 5% vs. 75. 9%).
Boosting3D: High-Fidelity Image-to-3D by Boosting 2D Diffusion Prior to 3D Prior with Progressive Learning
After the progressive training, the LoRA learns the 3D information of the generated object and eventually turns to an object-level 3D prior.
DreaMoving: A Human Video Generation Framework based on Diffusion Models
In this paper, we present DreaMoving, a diffusion-based controllable video generation framework to produce high-quality customized human videos.
DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors
Extensive experiments demonstrate that the proposed framework achieves excellent results in both domain adaptation and text-to-avatar tasks, outperforming existing methods in terms of generation quality and efficiency.
En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data
We present En3D, an enhanced generative scheme for sculpting high-quality 3D human avatars.
WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope
This paper introduces the WordArt Designer API, a novel framework for user-driven artistic typography synthesis utilizing Large Language Models (LLMs) on ModelScope.
DivAvatar: Diverse 3D Avatar Generation with a Single Prompt
We design DivAvatar, a novel framework that generates diverse avatars, empowering 3D creatives with a multitude of distinct and richly varied 3D avatars from a single text prompt.
Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception
Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks.
ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion Model
Specifically, we propose a shoe-wearing system, called Shoe-Model, to generate plausible images of human legs interacting with the given shoes.
Strictly-ID-Preserved and Controllable Accessory Advertising Image Generation
Customized generative text-to-image models have the ability to produce images that closely resemble a given subject.
