13 papers
Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding
Donghui Feng, Fengxi Zhang, Changsheng Gao +6
Distributed deployment of large vision foundation models often partitions a ViT backbone and exchanges intermediate token features between computing nodes, making efficient feature…
JSCGC: Joint Source-Channel-Generation Coding for Wireless Generative Communications
Tong Wu, Zhiyong Chen, Guo Lu +4
Conventional communication systems, including both separation-based coding and learning-based joint source-channel coding (JSCC), are typically designed under Shannon's rate-distor…
Content-Aware Mamba for Learned Image Compression
Yunuo Chen, Zezheng Lyu, Bing He +6
Recent learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts conten…
OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
Yan Zhao, Zhengxue Cheng, Junxuan Zhang +4
Lossless compression is essential for efficient data storage and transmission. Although learning-based lossless compressors achieve strong results, most of them are designed for a…
SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors
Bing He, Jingnan Gao, Yunuo Chen +5
Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. Recent approaches lev…
H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting
Bing He, Yunuo Chen, Guo Lu +5
Dynamic scene reconstruction poses a persistent challenge in 3D vision. Deformable 3D Gaussian Splatting has emerged as an effective method for this task, offering real-time render…