33 citations · 45 across the 21 of their papers we have counts for
24 papers
MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space
Markus Karmann, Shile Li, Christian Internò +10
Joint Embedding Predictive Architectures (JEPAs) are a promising paradigm for learning task-agnostic latent world models without visual reconstruction. However, standard JEPA train…
MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer
Ziyi Wang, Siming Zheng, Yang Yang +5
Makeup-transfer applies the reference makeup to the source face while preserving the source identity. Despite advances in full-face editing by diffusion-based methods, strong regio…
Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework
Linxiao Shi, Siming Zheng, Zerong Wang +5
Existing mobile devices are constrained by compact optical designs, such as small apertures, which make it difficult to produce natural, optically realistic bokeh effects. Although…
CFG: Control Classifier-Free Guidance via Score Discrepancy Analysis
Jiayang Gao, Tianyi Zheng, Jiayang Zou +9
Classifier-Free Guidance (CFG) is a cornerstone of modern conditional diffusion models, yet its reliance on the fixed or heuristic dynamic guidance weight is predominantly empirica…
SDMatte: Grafting Diffusion Models for Interactive Matting
Longfei Huang, Yu Liang, Hao Zhang +6
Recent interactive matting methods have shown satisfactory performance in capturing the primary regions of objects, but they fall short in extracting fine-grained details in edge r…
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…
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…
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…
LLaVA-OneVision: Easy Visual Task Transfer
Bo Li, Yuanhan Zhang, Dong Guo +8
We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed by consolidating our insights into data, models, and visual representations in the LLaVA-NeXT…
SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging
Lingtong Kong, Bo Li, Yike Xiong +3
Multi-exposure High Dynamic Range (HDR) imaging is a challenging task when facing truncated texture and complex motion. Existing deep learning-based methods have achieved great suc…
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…
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…
Crafter: Facial Feature Crafting against Inversion-based Identity Theft on Deep Models
Shiming Wang, Zhe Ji, Liyao Xiang +4
With the increased capabilities at the edge (e.g., mobile device) and more stringent privacy requirement, it becomes a recent trend for deep learning-enabled applications to pre-pr…
Revisiting Single Image Reflection Removal In the Wild
Yurui Zhu, Xueyang Fu, Peng-Tao Jiang +5
This research focuses on the issue of single-image reflection removal (SIRR) in real-world conditions, examining it from two angles: the collection pipeline of real reflection pair…
Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection
Lv Tang, Peng-Tao Jiang, Zhihao Shen +3
In this paper, we introduce a novel multimodal camo-perceptive framework (MMCPF) aimed at handling zero-shot Camouflaged Object Detection (COD) by leveraging the powerful capabilit…