923 citations · 1k across the 25 of their papers we have counts for
26 papers
Ground4D: Consistency-Aware 4D Reconstruction from Monocular Video
Qing Zhao, Weijian Deng, Pengxu Wei +1
Learning a 4D scene representation from a single monocular video that supports dynamic novel-view synthesis while maintaining faithful geometry over time remains challenging. Dynam…
Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection
Zijie Cao, Weijie Tu, Yao Xiao +3
Detecting AI-generated images (AIGI) remains challenging because detectors often fail to generalize to unseen generators. Although existing methods are trained on large datasets, t…
Thinking Before You Speak: A Proactive Test-time Scaling Approach
Cong Liu, Wenchang Chai, Hejun Wu +3
Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and thos…
Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions
ZiYi Dong, Chengxing Zhou, Weijian Deng +3
Contemporary diffusion models built upon U-Net or Diffusion Transformer (DiT) architectures have revolutionized image generation through transformer-based attention mechanisms. The…
Decoder-Only LLMs are Better Controllers for Diffusion Models
Ziyi Dong, Yao Xiao, Pengxu Wei +1
Groundbreaking advancements in text-to-image generation have recently been achieved with the emergence of diffusion models. These models exhibit a remarkable ability to generate hi…
SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection
Huafeng Chen, Pengxu Wei, Guangqian Guo +1
Most Camouflaged Object Detection (COD) methods heavily rely on mask annotations, which are time-consuming and labor-intensive to acquire. Existing weakly-supervised COD approaches…
Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior
Yukai Shi, Yupei Lin, Pengxu Wei +3
Recently, researchers have proposed various deep learning methods to accurately detect infrared targets with the characteristics of indistinct shape and texture. Due to the limited…
IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images
Meilin Wang, Yexing Song, Pengxu Wei +3
Deep learning technologies have demonstrated their effectiveness in removing cloud cover from optical remote-sensing images. Convolutional Neural Networks (CNNs) exert dominance in…
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
Pengxu Wei, Yujing Sun, Xingbei Guo +4
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especial…
Identity-Preserving Talking Face Generation with Landmark and Appearance Priors
Weizhi Zhong, Chaowei Fang, Yinqi Cai +4
Generating talking face videos from audio attracts lots of research interest. A few person-specific methods can generate vivid videos but require the target speaker's videos for tr…
Masked Images Are Counterfactual Samples for Robust Fine-tuning
Yao Xiao, Ziyi Tang, Pengxu Wei +2
Deep learning models are challenged by the distribution shift between the training data and test data. Recently, the large models pre-trained on diverse data have demonstrated unpr…
DQnet: Cross-Model Detail Querying for Camouflaged Object Detection
Wei Sun, Chengao Liu, Linyan Zhang +6
Camouflaged objects are seamlessly blended in with their surroundings, which brings a challenging detection task in computer vision. Optimizing a convolutional neural network (CNN)…
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
Zesen Cheng, Pengchong Qiao, Kehan Li +6
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although tremendo…
DreamArtist++: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter
Ziyi Dong, Pengxu Wei, Liang Lin
State-of-the-arts text-to-image generation models such as Imagen and Stable Diffusion Model have succeed remarkable progresses in synthesizing high-quality, feature-rich images wit…
Robust Real-World Image Super-Resolution against Adversarial Attacks
Jiutao Yue, Haofeng Li, Pengxu Wei +2
Recently deep neural networks (DNNs) have achieved significant success in real-world image super-resolution (SR). However, adversarial image samples with quasi-imperceptible noises…
Adversarially-Aware Robust Object Detector
Ziyi Dong, Pengxu Wei, Liang Lin
Object detection, as a fundamental computer vision task, has achieved a remarkable progress with the emergence of deep neural networks. Nevertheless, few works explore the adversar…
Real-World Image Super-Resolution by Exclusionary Dual-Learning
Hao Li, Jinghui Qin, Zhijing Yang +4
Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attent…
Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution
Xiaoqian Xu, Pengxu Wei, Weikai Chen +3
Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super…
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
Ren Yang, Radu Timofte, Meisong Zheng +75
This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video. In this challenge, we proposed the LDV 2.0 dataset, which includes the…
Open Set Domain Adaptation By Novel Class Discovery
Jingyu Zhuang, Ziliang Chen, Pengxu Wei +2
In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain. Due to the lack of their specif…
Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning
Junkai Huang, Chaowei Fang, Weikai Chen +5
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. Whil…
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
Pengxu Wei, Hannan Lu, Radu Timofte +68
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This ch…
Component Divide-and-Conquer for Real-World Image Super-Resolution
Pengxu Wei, Ziwei Xie, Hannan Lu +4
In this paper, we present a large-scale Diverse Real-world image Super-Resolution dataset, i.e., DRealSR, as well as a divide-and-conquer Super-Resolution (SR) network, exploring t…
A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models
Yang Wu, Pengxu Wei, Liang Lin
In this paper, we propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs). From a perspective of physical simulation, we redefine th…