48 citations · 107 across the 23 of their papers we have counts for
23 papers
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
Xiao Cao, Yansong Qu, Xiangzhen +8
Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, existing methods struggle whe…
RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation
Shuang Zeng, Boxu Xie, Lei Zhu +6
Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotations that are costly and tim…
HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding
Xuerui Qiu, Yutao Cui, Guozhen Zhang +10
Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for gener…
Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context
JiaKui Hu, Jialun Liu, Liying Yang +7
Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory f…
Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing
Jialun Liu, Tian Li, Xiao Cao +20
Recent advances in diffusion-based video generation have substantially improved visual fidelity and temporal coherence. However, most existing approaches remain task-specific and r…
Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generation
Liying Yang, Jialun Liu, Jiakui Hu +5
Generating high-quality 4D objects with spatial-temporal consistency is still formidable. Existing diffusion-based methods often struggle with spatial-temporal inconsistency, as th…
Bridging Degradation Discrimination and Generation for Universal Image Restoration
JiaKui Hu, Zhengjian Yao, Lujia Jin +1
Universal image restoration is a critical task in low-level vision, requiring the model to remove various degradations from low-quality images to produce clean images with rich det…
Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration
Zhengjian Yao, Jiakui Hu, Kaiwen Li +5
Blind face restoration remains a persistent challenge due to the inherent ill-posedness of reconstructing holistic structures from severely constrained observations. Current genera…
AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs
Xinliang Zhang, Lei Zhu, Hangzhou He +5
Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of pat…
Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images
JiaKui Hu, Shanshan Zhao, Qing-Guo Chen +6
This paper presents Omni-View, which extends the unified multimodal understanding and generation to 3D scenes based on multiview images, exploring the principle that "generation fa…
Universal Image Restoration Pre-training via Masked Degradation Classification
JiaKui Hu, Zhengjian Yao, Lujia Jin +2
This study introduces a Masked Degradation Classification Pre-Training method (MaskDCPT), designed to facilitate the classification of degradation types in input images, leading to…
Chat-CBM: Towards Interactive Concept Bottleneck Models with Frozen Large Language Models
Hangzhou He, Lei Zhu, Kaiwen Li +5
Concept Bottleneck Models (CBMs) provide inherent interpretability by first predicting a set of human-understandable concepts and then mapping them to labels through a simple class…
Auto-Regressively Generating Multi-View Consistent Images
JiaKui Hu, Yuxiao Yang, Jialun Liu +3
Generating multi-view images from human instructions is crucial for 3D content creation. The primary challenges involve maintaining consistency across multiple views and effectivel…
Enhancing Image Restoration Transformer via Adaptive Translation Equivariance
JiaKui Hu, Zhengjian Yao, Lujia Jin +2
Translation equivariance is a fundamental inductive bias in image restoration, ensuring that translated inputs produce translated outputs. Attention mechanisms in modern restoratio…
NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li, Yeying Jin, Xin Jin +134
This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images. This challenge received a wide range of impressive solutions, which are devel…
Universal Image Restoration Pre-training via Degradation Classification
JiaKui Hu, Lujia Jin, Zhengjian Yao +1
This paper proposes the Degradation Classification Pre-Training (DCPT), which enables models to learn how to classify the degradation type of input images for universal image resto…
Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation
Zhenxin Lei, Man Yao, Jiakui Hu +4
Spiking Neural Networks (SNNs) have a low-power advantage but perform poorly in image segmentation tasks. The reason is that directly converting neural networks with complex archit…
Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training
Man Yao, Xuerui Qiu, Tianxiang Hu +7
The ambition of brain-inspired Spiking Neural Networks (SNNs) is to become a low-power alternative to traditional Artificial Neural Networks (ANNs). This work addresses two major c…
TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting
Bojun Xiong, Jialun Liu, Jiakui Hu +6
Physically Based Rendering (PBR) materials play a crucial role in modern graphics, enabling photorealistic rendering across diverse environment maps. Developing an effective and ef…
High-Performance Temporal Reversible Spiking Neural Networks with Training Memory and Inference Cost
JiaKui Hu, Man Yao, Xuerui Qiu +6
Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods ca…
Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips
Man Yao, Jiakui Hu, Tianxiang Hu +5
Neuromorphic computing, which exploits Spiking Neural Networks (SNNs) on neuromorphic chips, is a promising energy-efficient alternative to traditional AI. CNN-based SNNs are the c…
Inherent Redundancy in Spiking Neural Networks
Man Yao, Jiakui Hu, Guangshe Zhao +4
Spiking Neural Networks (SNNs) are well known as a promising energy-efficient alternative to conventional artificial neural networks. Subject to the preconceived impression that SN…
Spike-driven Transformer
Man Yao, Jiakui Hu, Zhaokun Zhou +4
Spiking Neural Networks (SNNs) provide an energy-efficient deep learning option due to their unique spike-based event-driven (i.e., spike-driven) paradigm. In this paper, we incorp…