IEEE

Mixed-Precision Post-Training Quantization for Learned Image Compression

Abstract: With the rapid development of neural networks, learned image compression (LIC) has surpassed traditional methods in the field of image compression. However, current LIC frameworks rely on ...
GitHub

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

This is the official repository of paper Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching. We propose Distilled Decoding (DD) to distill a pre-trained image ...
IEEE

Three-Dimensional Signal Processing: A New Approach in Dynamical Sampling Via Tensor Products

Abstract: The dynamical sampling problem is centered around reconstructing signals that evolve over time according to a dynamical process, from spatial-temporal samples that may be noisy. This topic ...
GitHub

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization

This repo contains the official code of our ECCV2024 paper: MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization We design MixDQ, a ...