Yuefeng Zhang

HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression

HAMP-LIC is proposed, a Hessian-aware mixed-precision post-training quantization (PTQ) framework with a four-stage optimization strategy that consistently outperforms existing fixed- and mixed-precision PTQ methods across multiple datasets while completely eliminating cross-platform encoding-decoding errors.