6 papers
Towards Practical Lossless Neural Compression for LiDAR Point Clouds
Pengpeng Yu, Haoran Li, Runqing Jiang +4
LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the co…
CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting
Pengpeng Yu, Runqing Jiang, Qi Zhang +3
While feed-forward 3D Gaussian splatting reconstructs renderable Gaussian primitives from sparse context views without per-scene optimization, existing pipelines do not provide a c…
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…
Robust Multi-generation Learned Compression of Point Cloud Attribute
Xiangzuo Liu, Zhikai Liu, PengPeng Yu +2
Existing learned point cloud attribute compression methods primarily focus on single-pass rate-distortion optimization, while overlooking the issue of cumulative distortion in mult…
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…