activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models

Zhuoyuan Li, Rui Zhao, Jin Wang +5

Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in…

cs.CV2026

Current Injection Spiking Neural Network for Infrared and Visible Image Fusion

Rui Zhao, Zhuoyuan Li, Wenrui Li +4

Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content. While existing methods are largel…

cs.CV2026

RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting

Hoang-Nhat Tran, Francesco Di Sario, Gabriele Spadaro +2

Recent advances in neural scene representations have transformed immersive multimedia, with 3D Gaussian Splatting (3DGS) enabling real-time photorealistic rendering. Despite its ef…

cs.CV2025

Generative Models at the Frontier of Compression: A Survey on Generative Face Video Coding

Bolin Chen, Shanzhi Yin, Goluck Konuko +4

The rise of deep generative models has greatly advanced video compression, reshaping the paradigm of face video coding through their powerful capability for semantic-aware represen…

cs.CV2025

Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates

Gabriele Spadaro, Alberto Presta, Jhony H. Giraldo +5

Efficient compression of low-bit-rate point clouds is critical for bandwidth-constrained applications. However, existing techniques mainly focus on high-fidelity reconstruction, re…

cs.CV2025

Language-Guided Visual Perception Disentanglement for Image Quality Assessment and Conditional Image Generation

Zhichao Yang, Leida Li, Pengfei Chen +2

Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-s…