← Back to Model Beat
Open Source·3d ago·all news from November 19, 2026

LIC-Audit: How Comparable Are Reported Gains in Learned Image Compression?

arXiv:2611.23419v1 Announce Type: cross Abstract: Learned image compression (LIC) papers often report BD-rate improvements of only a few percent. They are measured against VTM reference software whose version keeps changing: the claims we audit name 7 versions, 5 in 2025 papers alone. But how comparable are these numbers across papers, and what evidence should future papers give for such small gains? We introduce LIC-Audit, an analysis of 353 released rate-distortion curves from 36 repositories, and a controlled re-evaluation of eight public codec releases with 28,193 encode-decode records. We identify three problems. First, different VTM reference runs change BD-rates by up to 3.56 percentage points, and on CLIC Pro published numbers order 10 of 55 method pairs differently from a common computation; comparing codecs directly over a fixed quality range removes this dependence. Second, releases use different and mostly undocumented conventions for counting bits, computing PSNR, and padding images. Under consistent…

Covered by 1 source

  • AarXiv CS.AI↗Haisheng Fu, Jie Liang, Runyu Yang, Feng Ding, Xin Dong, Zixiao Jin, Jingning Han3d ago

Related stories

Open SourceLean and Mathlib community officially confirms Levent Alpöge's proof of the Riemann hypothesis is correctNov 22Open SourceReports of AI-generated child sexual abuse material have surged more than 8,400 percent in two yearsNov 16 · 3 sourcesOpen SourceAt Holiday Extras, dots get to work before anyone asksNov 16Open SourceHugging Face and OpenRouter join forces to make open-weight models easy to runNov 16