4 papers
Re-Densification Meets Cross-Scale Propagation: Real-Time Neural Compression of LiDAR Point Clouds
Pengpeng Yu, Haoran Li, Runqing Jiang +3
LiDAR point clouds are fundamental to various applications, yet high-precision scans incur substantial storage and transmission overhead. Existing methods typically convert unorder…
PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models
Yongjian Zhang, Longguang Wang, Kunhong Li +4
This work presents PanMatch, a versatile foundation model for robust correspondence matching. Unlike previous methods that rely on task-specific architectures and domain-specific f…
Pack-PTQ: Advancing Post-training Quantization of Neural Networks by Pack-wise Reconstruction
Changjun Li, Runqing Jiang, Zhuo Song +3
Post-training quantization (PTQ) has evolved as a prominent solution for compressing complex models, which advocates a small calibration dataset and avoids end-to-end retraining. H…
AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers
Runqing Jiang, Ye Zhang, Longguang Wang +2
Post-training quantization (PTQ) has emerged as a promising solution for reducing the storage and computational cost of vision transformers (ViTs). Recent advances primarily target…