Search Results for author:
Found 18 papers, 9 papers with code
A$^\text{T}$A: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting
Existing background inpainting methods typically strictly preserve the subject's original position from the source image, resulting in inconsistencies between the subject and the generated background.
Image Inversion: A Survey from GANs to Diffusion and Beyond
This paper provides a comprehensive review of the latest advancements in image inversion techniques, focusing on two main paradigms: Generative Adversarial Network (GAN) inversion and diffusion model inversion.
Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction
Leveraging the rearranged codebook, we propose a Cluster-oriented Cross-entropy Loss that guides the model to correctly predict the cluster where the token is located.
EMOv2: Pushing 5M Vision Model Frontier
Our goal is to set up the new frontier of the 5M magnitude lightweight model on various downstream tasks.
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.
AttentionPainter: An Efficient and Adaptive Stroke Predictor for Scene Painting
Stroke-based Rendering (SBR) aims to decompose an input image into a sequence of parameterized strokes, which can be rendered into a painting that resembles the input image.
SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
Inspired by model pruning which lightens large pre-trained models by removing unimportant parameters, we propose a novel model fine-tuning method to make full use of these ineffective parameters and enable the pre-trained model with new task-specified capabilities.
DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation
In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part.
SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis
Then, we propose a two-stage self-training framework, where a coarse-stage model is employed to reconstruct the main structure and a refinement-stage model is used for enriching the details.
MotionMaster: Training-free Camera Motion Transfer For Video Generation
Furthermore, we propose a few-shot camera motion disentanglement method to extract the common camera motion from multiple videos with similar camera motions, which employs a window-based clustering technique to extract the common features in temporal attention maps of multiple videos.
Plasticine3D: 3D Non-Rigid Editing with Text Guidance by Multi-View Embedding Optimization
With the help of Score Distillation Sampling (SDS) and the rapid development of neural 3D representations, some methods have been proposed to perform 3D editing such as adding additional geometries, or overwriting textures.
AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
Existing anomaly inspection methods are limited in their performance due to insufficient anomaly data.
SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Model
Vector graphics are widely used in graphical designs and have received more and more attention.
Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region
To solve the problem, we propose Compositional Neural Painter, a novel stroke-based rendering framework which dynamically predicts the next painting region based on the current canvas, instead of dividing the image plane uniformly into painting regions.
Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption
To address these problems, we propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss, which targets different learning objectives at distinct training stages of the diffusion model.
DocPrompt: Large-scale continue pretrain for zero-shot and few-shot document question answering
In this paper, we propose Docprompt for document question answering tasks with powerful zero-shot and few-shot performance.
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding.
Ranked #2 on
Semantic entity labeling
on FUNSD
Audio Injection Adversarial Example Attack
We study the problem of audio adversarial example attacks with sparse perturbations.
