From the 1 of 5 linked papers with an AI index.
5 papers
Flexible Deep Joint Source-Channel Coding: A Vibrotactile Example
Shuijie Li, Kemi Chen, Runjie Wang +2
The increasing demand for real-time tactile communication in multimedia systems has exposed the limitations of existing Joint Source-Channel Coding (JSCC) techniques. While current…
ParaJSCC: A Parameterized Framework for Reusable Multimodal Joint Source-Channel Coding
Kemi Chen, Mingkai Chen, Youjia Chen +3
Multimodal signals, such as visual, audio, and tactile data, are increasingly maintained as persistent digital assets in immersive communication systems and digital twins. In these…
Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction
Junhong Lin, Jinlong Wang, Xianda Guo +6
Single-frame surround-view reconstruction faces severe geometric instability and rendering artifacts due to minimal inter-camera overlap. While existing methods rely on complex dec…
SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM
Jingxuan Su, Shenglin Wang, Tiesong Zhao +2
The paper introduces SpatialQ, a multimodal framework that assesses the visual quality of 3D Gaussian Splatting scenes by combining view-specific image features, depth and point‑cl…
Bio-SFT: Asymmetric Cortical Guidance and Retinal Adaptation for Robust HDR Reconstruction
Tingyu Cheng, Ting Zhang, Chongyi Li +2
Recovering high dynamic range (HDR) radiance from a single standard dynamic range (SDR) image is highly ill-posed. Extreme luminance variation and severe quantization in dark regio…