GSVC: Efficient Video Representation and Compression Through 2D Gaussian Splatting
cs.CV, cs.MM
Submitted: 2025-01-21
Updated: 2026-10-28
Comments: 23 pages, 15 figures, 1 table. Extended version of our NOSSDAV 2025 paper
Project page: https://yuang-ian.github.io/gsvc
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- VeGaS: Video Gaussian Splatting
- Splatter a Video: Video Gaussian Representation for Versatile Processing
- gsplat: An Open-Source Library for Gaussian Splatting
- Image-GS: Content-Adaptive Image Representation via 2D Gaussians
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs