From the 2 of 4 linked papers with an AI index.
4 papers
Efficient LiDAR Reflectance Compression via Scanning Serialization
Jiahao Zhu, Kang You, Dandan Ding +1
The paper introduces SerLiC, a neural compression framework that serializes LiDAR point clouds into 1D scan-order sequences and uses a Mamba-based model to efficiently compress ref…
SpeedyGS: Content-Aware 3D Gaussian Splatting Compression via Two-Stage Optimization
Junteng Zhang, Tong Chen, Yuxin Zhao +3
SpeedyGS is a two‑stage compressor for 3D Gaussian Splatting scenes that jointly optimizes adaptive quantization and pruning with a lightweight rate proxy, then encodes geometry vi…
PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression
Jiahao Zhu, Kang You, Dandan Ding +1
LiDAR point cloud compression is vital for autonomous systems to handle massive data from high-resolution sensors. While learned entropy modeling built upon octree structures yield…
RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds
Kang You, Tong Chen, Dandan Ding +2
Despite the substantial advancements demonstrated by learning-based neural models in the LiDAR Point Cloud Compression (LPCC) task, realizing real-time compression - an indispensab…