UniComp: Rethinking Video Compression Through Informational Uniqueness

TL;DR

UniComp introduces an information-theoretic video compression framework that leverages the concept of information uniqueness to optimize token selection and spatial compression, outperforming existing methods under limited computational resources.

Contribution

The paper proposes a novel information uniqueness-based approach for video compression, including new modules for semantic grouping, adaptive allocation, and spatial compression.

Findings

Outperforms existing methods in preserving visual information under limited budgets

Demonstrates the effectiveness of information uniqueness in token compression

Achieves superior reconstruction fidelity compared to traditional approaches

Abstract

Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to maximize the information fidelity of video representations under constrained computational budgets. Starting from the information-theoretic perspective, we formulate the vision compression as an optimization problem that minimizes conditional entropy (reconstruction error) between retained and full tokens. To achieve this, we introduce the notion of information uniqueness to measure intrinsic redundancy among tokens to link with reconstruction error. Based on uniqueness, we design three modules-Frame Group Fusion, Token Allocation, and Spatial Dynamic Compression-that progressively perform semantic frame grouping, adaptive resource allocation, and fine-grained spatial compression. Extensive experiments demonstrate that UniComp consistently outperforms existing compression methods in preserving essential visual tokens under limited computational budgets, highlighting the pivotal role of information uniqueness in token compression efficacy.