Search Results for author:
Found 30 papers, 15 papers with code
Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration
Instead of directly using Vision-RWKV, we replace the original Q-Shift in RWKV with a Depth-wise Convolution shift to better model local dependencies, combined with Bi-directional attention for comprehensive linear attention.
DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation
To enhance the controllability of text-to-image diffusion models, current ControlNet-like models have explored various control signals to dictate image attributes.
Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target contents.
FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on
Although image-based virtual try-on has made considerable progress, emerging approaches still encounter challenges in producing high-fidelity and robust fitting images across diverse scenarios.
Ranked #2 on
Virtual Try-on
on VITON-HD
VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding
To tackle this issue widely existing in real-world scenarios, we propose VTON-HandFit, leveraging the power of hand priors to reconstruct the appearance and structure for hand occlusion cases.
Oracle Bone Inscriptions Multi-modal Dataset
Oracle bone inscriptions(OBI) is the earliest developed writing system in China, bearing invaluable written exemplifications of early Shang history and paleography.
RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network
In the second component, we design a lightweight facial identity alignment (FIA) module which includes a lip-shape control structure and a face texture reference structure.
DF40: Toward Next-Generation Deepfake Detection
In this work, we found the dataset (both train and test) can be the "primary culprit" due to: (1) forgery diversity: Deepfake techniques are commonly referred to as both face forgery and entire image synthesis.
CustAny: Customizing Anything from A Single Example
The primary issue of promoting zero-shot object customization from specific domains to the general domain is to establish a large-scale general ID dataset for model pre-training, which is time-consuming and labor-intensive.
NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
Multimodal large language models (MLLMs) contribute a powerful mechanism to understanding visual information building on large language models.
ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model
Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images.
DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation
Aiming to simultaneously generate the object and its matting annotation, we build a matting head to make a green color removal in the latent space of the VAE decoder.
ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis
As a pure convolution structure, ModernTCN still achieves the consistent state-of-the-art performance on five mainstream time series analysis tasks while maintaining the efficiency advantage of convolution-based models, therefore providing a better balance of efficiency and performance than state-of-the-art Transformer-based and MLP-based models.
PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization
Moreover, these methods often grapple with identity distortion and limited expression diversity.
Dynamic Frame Interpolation in Wavelet Domain
Video frame interpolation is an important low-level vision task, which can increase frame rate for more fluent visual experience.
A Unified Framework for 3D Point Cloud Visual Grounding
This elaborate design enables 3DRefTR to achieve both well-performing 3DRES and 3DREC capacities with only a 6% additional latency compared to the original 3DREC model.
Cross-LKTCN: Modern Convolution Utilizing Cross-Variable Dependency for Multivariate Time Series Forecasting Dependency for Multivariate Time Series Forecasting
The past few years have witnessed the rapid development in multivariate time series forecasting.
Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection
To address this issue, we propose a two-branch approach that consists of a local branch for detecting structural anomalies and a global branch for detecting logical anomalies.
Ranked #22 on
Anomaly Detection
on MVTec LOCO AD
High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets
A generic method for generating a high-quality image from the degraded one is in demand.
Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution
Although some Unsupervised Degradation Prediction (UDP) methods are proposed to bypass this problem, the \textit{inconsistency} between degradation embedding and SR feature is still challenging.
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications.
Ranked #1 on
Video Frame Interpolation
on Middlebury
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.
Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution
In this paper, we propose a novel blind SR framework to super-resolve LR images degraded by arbitrary blur kernel with accurate kernel estimation in frequency domain.
Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
Temporal action localization is an important yet challenging task in video understanding.
Learning Comprehensive Motion Representation for Action Recognition
For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame.
Temporal Distinct Representation Learning for Action Recognition
Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos.
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods.
Ranked #2 on
Optical Flow Estimation
on KITTI 2012 unsupervised
TEINet: Towards an Efficient Architecture for Video Recognition
To relieve this problem, we propose an efficient temporal module, termed as Temporal Enhancement-and-Interaction (TEI Module), which could be plugged into the existing 2D CNNs (denoted by TEINet).
Fast Learning of Temporal Action Proposal via Dense Boundary Generator
In this paper, we propose an efficient and unified framework to generate temporal action proposals named Dense Boundary Generator (DBG), which draws inspiration from boundary-sensitive methods and implements boundary classification and action completeness regression for densely distributed proposals.
Ranked #9 on
Temporal Action Localization
on FineAction
Image Matching via Loopy RNN
Towards this end, we propose a novel loopy recurrent neural network (Loopy RNN), which is capable of aggregating relationship information of two input images in a progressive/iterative manner and outputting the consolidated matching score in the final iteration.
