19 papers
Learning Adaptive Semantic Gaussian Allocation for 3D Occupancy
Kanglin Ning, Yiran Zhao, Wenrui Li +4
Semantic 3D Gaussians provide a compact representation for 3D semantic occupancy prediction by rendering semantic primitives into a voxel volume under voxel-wise supervision. Recen…
Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization
Zhe Yang, Ruyi Zhang, Hongtao Chen +4
Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events, including categories unseen during training.…
Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach
Kanglin Ning, Yiran Zhao, Wenrui Li +3
Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remains a significant challenge.…
PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting
Hantang Li, Qiang Zhu, Xiandong Meng +3
Dropout-based sparse-view 3D Gaussian Splatting (3DGS) methods alleviate overfitting by randomly suppressing Gaussian primitives during training. Existing methods mainly focus on d…
Hyperbolic Distillation: Geometry-Guided Cross-Modal Transfer for Robust 3D Object Detection
Kanglin Ning, Wenrui Li, Houde Quan +3
Cross-modal knowledge distillation has emerged as an effective strategy for integrating point cloud and image features in 3D perception tasks. However, the modality heterogeneity,…
All-in-One Video Restoration under Smoothly Evolving Unknown Weather Degradations
Wenrui Li, Hongtao Chen, Yao Xiao +4
All-in-one image restoration aims to recover clean images from diverse unknown degradations using a single model. But extending this task to videos faces unique challenges. Existin…
RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming
Jisheng Chu, Wenrui Li, Rui Zhao +3
Generating immersive 3D scenes from texts is a core task in computer vision, crucial for applications in virtual reality and game development. Despite the promise of leveraging 2D…
Adaptive Redundancy Regulation for Balanced Multimodal Information Refinement
Zhe Yang, Wenrui Li, Hongtao Chen +3
Multimodal learning aims to improve performance by leveraging data from multiple sources. During joint multimodal training, due to modality bias, the advantaged modality often domi…
Hyperbolic Hierarchical Alignment Reasoning Network for Text-3D Retrieval
Wenrui Li, Yidan Lu, Yeyu Chai +3
With the daily influx of 3D data on the internet, text-3D retrieval has gained increasing attention. However, current methods face two major challenges: Hierarchy Representation Co…
Language-Guided Graph Representation Learning for Video Summarization
Wenrui Li, Wei Han, Hengyu Man +3
With the rapid growth of video content on social media, video summarization has become a crucial task in multimedia processing. However, existing methods face challenges in capturi…
PAGCNet: A Pose-Aware and Geometry Constrained Framework for Panoramic Depth Estimation
Kanglin Ning, Ruzhao Chen, Penghong Wang +3
Explicitly modeling room background depth as a geometric constraint has proven effective for panoramic depth estimation. However, reconstructing this background depth for regular e…
DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation
Kefei Zhu, Fengshuo Bai, YuanHao Xiang +8
Dexterous manipulation is critical for advancing robot capabilities in real-world applications, yet diverse and high-quality datasets remain scarce. Existing data collection method…
Spiking Variational Graph Representation Inference for Video Summarization
Wenrui Li, Wei Han, Liang-Jian Deng +2
With the rise of short video content, efficient video summarization techniques for extracting key information have become crucial. However, existing methods struggle to capture the…
Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning
Wenrui Li, Penghong Wang, Xingtao Wang +3
Audio-visual zero-shot learning (ZSL) has been extensively researched for its capability to classify video data from unseen classes during training. Nevertheless, current methodolo…
RouteWinFormer: A Route-Window Transformer for Middle-range Attention in Image Restoration
Qifan Li, Tianyi Liang, Xingtao Wang +1
Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention of…
Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images
Wenrui Li, Zhe Yang, Wei Han +3
Reconstructing desired objects and scenes has long been a primary goal in 3D computer vision. Single-view point cloud reconstruction has become a popular technique due to its low c…
Digging into Intrinsic Contextual Information for High-fidelity 3D Point Cloud Completion
Jisheng Chu, Wenrui Li, Xingtao Wang +3
The common occurrence of occlusion-induced incompleteness in point clouds has made point cloud completion (PCC) a highly-concerned task in the field of geometric processing. Existi…
Riemann-based Multi-scale Attention Reasoning Network for Text-3D Retrieval
Wenrui Li, Wei Han, Yandu Chen +4
Due to the challenges in acquiring paired Text-3D data and the inherent irregularity of 3D data structures, combined representation learning of 3D point clouds and text remains une…
SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splatting
Wenrui Li, Fucheng Cai, Yapeng Mi +4
Text-driven 3D scene generation has seen significant advancements recently. However, most existing methods generate single-view images using generative models and then stitch them…