2.5k citations · 2.8k across the 32 of their papers we have counts for
35 papers
A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
Quan-Sheng Zeng, Yunheng Li, Qilong Wang +4
Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression…
Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution
Tianyi Zhang, Zheng-Peng Duan, Peng-Tao Jiang +4
Diffusion-based real-world image super-resolution (Real-ISR) methods have demonstrated impressive performance.To achieve efficient Real-ISR, many works employ Variational Score Dis…
Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment
Zhuoxuan Cai, Jian Zhang, Xinbin Yuan +7
Recent studies demonstrate that multimodal large language models (MLLMs) can proficiently evaluate visual quality through interpretable assessments. However, existing approaches ty…
Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
Xinbin Yuan, Jian Zhang, Kaixin Li +8
Graphical User Interface (GUI) agents have made substantial strides in understanding and executing user instructions across diverse platforms. Yet, grounding these instructions to…
HyperMotionX: The Dataset and Benchmark with DiT-Based Pose-Guided Human Image Animation of Complex Motions
Shuolin Xu, Siming Zheng, Ziyi Wang +7
Recent advances in diffusion models have significantly improved conditional video generation, particularly in the pose-guided human image animation task. Although existing methods…
MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-on
Guangyuan Li, Siming Zheng, Hao Zhang +6
Video Virtual Try-On (VVT) aims to synthesize garments that appear natural across consecutive video frames, capturing both their dynamics and interactions with human motion. Despit…
Photography Perspective Composition: Towards Aesthetic Perspective Recommendation
Lujian Yao, Siming Zheng, Xinbin Yuan +5
Traditional photography composition approaches are dominated by 2D cropping-based methods. However, these methods fall short when scenes contain poorly arranged subjects. Professio…
A Temporal Modeling Framework for Video Pre-Training on Video Instance Segmentation
Qing Zhong, Peng-Tao Jiang, Wen Wang +3
Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos.…
M2N2V2: Multi-Modal Unsupervised and Training-free Interactive Segmentation
Markus Karmann, Peng-Tao Jiang, Bo Li +1
We present Markov Map Nearest Neighbor V2 (M2N2V2), a novel and simple, yet effective approach which leverages depth guidance and attention maps for unsupervised and training-free…
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation
Ziyang Song, Zerong Wang, Bo Li +5
Monocular depth estimation within the diffusion-denoising paradigm demonstrates impressive generalization ability but suffers from low inference speed. Recent methods adopt a singl…
Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning
Yuti Liu, Shice Liu, Junyuan Gao +4
Image Aesthetic Assessment (IAA) is a vital and intricate task that entails analyzing and assessing an image's aesthetic values, and identifying its highlights and areas for improv…
CPA: Camera-pose-awareness Diffusion Transformer for Video Generation
Yuelei Wang, Jian Zhang, Pengtao Jiang +3
Despite the significant advancements made by Diffusion Transformer (DiT)-based methods in video generation, there remains a notable gap with controllable camera pose perspectives.…
Learning Adaptive Lighting via Channel-Aware Guidance
Qirui Yang, Peng-Tao Jiang, Hao Zhang +4
Learning lighting adaptation is a crucial step in achieving good visual perception and supporting downstream vision tasks. Current research often addresses individual light-related…
Learning Differential Pyramid Representation for Tone Mapping
Qirui Yang, Yinbo Li, Yihao Liu +5
Existing tone mapping methods operate on downsampled inputs and rely on handcrafted pyramids to recover high-frequency details. These designs typically fail to preserve fine textur…
Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation
Ruihao Xia, Yu Liang, Peng-Tao Jiang +4
Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual…
Towards Natural Image Matting in the Wild via Real-Scenario Prior
Ruihao Xia, Yu Liang, Peng-Tao Jiang +5
Recent approaches attempt to adapt powerful interactive segmentation models, such as SAM, to interactive matting and fine-tune the models based on synthetic matting datasets. Howev…
ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution
Yuhao Wan, Peng-Tao Jiang, Qibin Hou +4
We present ControlSR, a new method that can tame Diffusion Models for consistent real-world image super-resolution (Real-ISR). Previous Real-ISR models mostly focus on how to activ…
Improving Consistency in Diffusion Models for Image Super-Resolution
Junhao Gu, Peng-Tao Jiang, Hao Zhang +4
Recent methods exploit the powerful text-to-image (T2I) diffusion models for real-world image super-resolution (Real-ISR) and achieve impressive results compared to previous models…
High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity
Qian Yu, Peng-Tao Jiang, Hao Zhang +4
In the realm of high-resolution (HR), fine-grained image segmentation, the primary challenge is balancing broad contextual awareness with the precision required for detailed object…
Scalable Visual State Space Model with Fractal Scanning
Lv Tang, HaoKe Xiao, Peng-Tao Jiang +3
Foundational models have significantly advanced in natural language processing (NLP) and computer vision (CV), with the Transformer architecture becoming a standard backbone. Howev…
Empowering Segmentation Ability to Multi-modal Large Language Models
Yuqi Yang, Peng-Tao Jiang, Jing Wang +4
Multi-modal large language models (MLLMs) can understand image-language prompts and demonstrate impressive reasoning ability. In this paper, we extend MLLMs' output by empowering M…
Boosting Box-supervised Instance Segmentation with Pseudo Depth
Xinyi Yu, Ling Yan, Pengtao Jiang +4
The realm of Weakly Supervised Instance Segmentation (WSIS) under box supervision has garnered substantial attention, showcasing remarkable advancements in recent years. However, t…
Multi-Task Dense Prediction via Mixture of Low-Rank Experts
Yuqi Yang, Peng-Tao Jiang, Qibin Hou +3
Previous multi-task dense prediction methods based on the Mixture of Experts (MoE) have received great performance but they neglect the importance of explicitly modeling the global…
Improving Adversarial Energy-Based Model via Diffusion Process
Cong Geng, Tian Han, Peng-Tao Jiang +4
Generative models have shown strong generation ability while efficient likelihood estimation is less explored. Energy-based models~(EBMs) define a flexible energy function to param…