7 papers
Video Codec-Guided Training-Free Token Compression for Video Large Language Models
Xihua Sheng, Ruijie Liu, Chang Wen Chen
Video large language models (VLLMs) rely on long visual token sequences to understand complex temporal content, which makes visual token compression important for efficient inferen…
OctMesh: A Unified Octree-Hierarchical Framework for Lossless Triangle Mesh Compression
Shiyu Feng, Xihua Sheng, Lingyu Zhu +2
Lossless triangle mesh compression must preserve both vertex positions and connectivity. Octrees support learned point cloud geometry coding and progressive refinement, but extendi…
URVC: A Unified Real-Time Neural Video Coding Model with Temporal, Spatial, and Perceptual Adaptivity
Xihua Sheng, Chang Wen Chen
Neural video coding has advanced rapidly, achieving competitive compression performance while also enabling real-time coding speed. Yet, existing codecs exhibit severe rigidity whe…
CADC: Content Adaptive Diffusion-Based Generative Image Compression
Xihua Sheng, Lingyu Zhu, Tianyu Zhang +3
Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential…
DCVC-MV: Deep Contextual Multiview Video Compression with Efficient Inter-View Prediction
Xihua Sheng, Yingwen Zhang, Long Xu +1
Multiview video is a key format for 3D applications such as free-viewpoint broadcasting and virtual reality, yet its large data volume poses significant challenges for efficient st…
Fine-Grained Motion Compression and Selective Temporal Fusion for Neural B-Frame Video Coding
Xihua Sheng, Peilin Chen, Meng Wang +3
With the remarkable progress in neural P-frame video coding, neural B-frame coding has recently emerged as a critical research direction. However, most existing neural B-frame code…
An Information-Theoretic Regularizer for Lossy Neural Image Compression
Yingwen Zhang, Meng Wang, Xihua Sheng +4
Lossy image compression networks aim to minimize the latent entropy of images while adhering to specific distortion constraints. However, optimizing the neural network can be chall…