14 papers
3DGSI-Assessor: A Large-Scale Dataset and An LMM-based Method for 3D Gaussian Splatting Image Quality Assessment
Yuke Xing, Jiarui Wang, William Gordon +3
3D Gaussian Splatting (3DGS) has become a dominant representation for real-time novel view synthesis (NVS), yet its storage footprint makes compression indispensable for practical…
HybridINR-PCGC: Hybrid Lossless Point Cloud Geometry Compression Bridging Pretrained Model and Implicit Neural Representation
Wenjie Huang, Qi Yang, Shuting Xia +3
Learning-based point cloud compression presents superior performance to handcrafted codecs. However, pretrained-based methods, which are based on end-to-end training and expected t…
Progressively Deformable 2D Gaussian Splatting for Video Representation at Arbitrary Resolutions
Mufan Liu, Qi Yang, Miaoran Zhao +4
Implicit neural representations (INRs) enable fast video compression and effective video processing, but a single model rarely offers scalable decoding across rates and resolutions…
TVMC: Time-Varying Mesh Compression via Multi-Stage Anchor Mesh Generation
He Huang, Qi Yang, Yiling Xu +2
Time-varying meshes, characterized by dynamic connectivity and varying vertex counts, hold significant promise for applications such as augmented reality. However, their practical…
Light4GS: Lightweight Compact 4D Gaussian Splatting Generation via Context Model
Mufan Liu, Qi Yang, He Huang +4
3D Gaussian Splatting (3DGS) has emerged as an efficient and high-fidelity paradigm for novel view synthesis. To adapt 3DGS for dynamic content, deformable 3DGS incorporates tempor…
Lightweight 3D Gaussian Splatting Compression via Video Codec
Qi Yang, Geert Van Der Auwera, Zhu Li
Current video-based GS compression methods rely on using Parallel Linear Assignment Sorting (PLAS) to convert 3D GS into smooth 2D maps, which are computationally expensive and tim…