# Fast MPEG-CDVS Encoder with GPU-CPU Hybrid Computing

## TL;DR

This paper presents a GPU-CPU hybrid implementation of the MPEG-CDVS encoder, significantly accelerating the process for large-scale visual search by optimizing parallel computation and data handling.

## Contribution

The paper introduces a novel GPU-CPU hybrid architecture for MPEG-CDVS encoding, achieving high speed and compatibility with CNN methods for scalable visual search.

## Key findings

- Significant speedup over traditional CPU-based encoders
- Effective GPU-CPU workload balancing and optimization
- Compatibility with CNN approaches enhances performance

## Abstract

The compact descriptors for visual search (CDVS) standard from ISO/IEC moving pictures experts group (MPEG) has succeeded in enabling the interoperability for efficient and effective image retrieval by standardizing the bitstream syntax of compact feature descriptors. However, the intensive computation of CDVS encoder unfortunately hinders its widely deployment in industry for large-scale visual search. In this paper, we revisit the merits of low complexity design of CDVS core techniques and present a very fast CDVS encoder by leveraging the massive parallel execution resources of GPU. We elegantly shift the computation-intensive and parallel-friendly modules to the state-of-the-arts GPU platforms, in which the thread block allocation and the memory access are jointly optimized to eliminate performance loss. In addition, those operations with heavy data dependence are allocated to CPU to resolve the extra but non-necessary computation burden for GPU. Furthermore, we have demonstrated the proposed fast CDVS encoder can work well with those convolution neural network approaches which has harmoniously leveraged the advantages of GPU platforms, and yielded significant performance improvements. Comprehensive experimental results over benchmarks are evaluated, which has shown that the fast CDVS encoder using GPU-CPU hybrid computing is promising for scalable visual search.