← 研踪 PaperTrailarXiv:2610.29691 · v2
Efficient Generative Image Compression with Quantized Latents Refinement
首次提交 2026-10-21 21:03
版本更新 2026-11-17 11:05
雷达观测 2026-11-18 19:43
摘要
Generative image compression (GIC) delivers strong perceptual quality. However, GIC methods with strong perceptual quality often rely on pretrained diffusion models with high latency, while recent lightweight GIC methods reduce latency but compromise perceptual quality. At low bitrates, coarse deterministic quantization can map nearby encoder latents representing different fine details to the same quantized point, making those details difficult to recover. Motivated by this, we propose GR-GIC which delivers competitive compression performance with fast inference. For better performance, we introduce Guided Refinement (GR), which combines latent refinement guided by entropy context with adaptive perturbations, jointly improving reconstruction at low bitrates. For fast inference, we introduce reorganized projected residual vector quantization, which equivalently reorganizes residual updates into low-dimensional lookups to expose greater parallelism and reduce latency. Experiments on Kodak show that GR-GIC achieves BD-rate savings of 22.09%, 42.14%, 19.35%, and 30.87% over OneDC for LPIPS, DISTS, PSNR, and FID, respectively. Moreover, our CUDA implementation encodes and decodes in 2.81 and 3.48 ms on an NVIDIA A100, achieving and speedups over the official OneDC implementation, respectively. We further evaluate GR-GIC on an NVIDIA Jetson Orin NX, demonstrating competitive coding speed on edge hardware.
作者备注:21 pages, 16 figures, including supplementary material
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-17 11:05 · 最新观测版本
Efficient Generative Image Compression with Quantized Latents Refinement
Generative image compression (GIC) delivers strong perceptual quality. However, GIC methods with strong perceptual quality often rely on pretrained diffusion models with high latency, while recent lightweight GIC methods reduce latency but compromise perceptual quality. At low bitrates, coarse deterministic quantization can map nearby encoder latents representing different fine details to the same quantized point, making those details difficult to recover. Motivated by this, we propose GR-GIC which delivers competitive compression performance with fast inference. For better performance, we introduce Guided Refinement (GR), which combines latent refinement guided by entropy context with adaptive perturbations, jointly improving reconstruction at low bitrates. For fast inference, we introduce reorganized projected residual vector quantization, which equivalently reorganizes residual updates into low-dimensional lookups to expose greater parallelism and reduce latency. Experiments on Kodak show that GR-GIC achieves BD-rate savings of 22.09%, 42.14%, 19.35%, and 30.87% over OneDC for LPIPS, DISTS, PSNR, and FID, respectively. Moreover, our CUDA implementation encodes and decodes in 2.81 and 3.48 ms on an NVIDIA A100, achieving and speedups over the official OneDC implementation, respectively. We further evaluate GR-GIC on an NVIDIA Jetson Orin NX, demonstrating competitive coding speed on edge hardware.
查看此版本解读 →查看此版本原文 ↗