VISART 2026 at ECCV calls papers as author benchmarks commercial vs local models on art catalog parsing
ducha_aiki · x · 2026-09-08
VISART VIII, the Vision for Art and Culture workshop at ECCV 2026 in Malmö, Sweden, is open for submissions across two tracks: technical CV-for-art papers (14 pages, in proceedings) and 4-page extended abstracts on critical reflections.
The poster also teases a comparison of commercial vs local vs mid-sized models for art catalogue parsing, tied to the workshop's research agenda on digitised artworks and cultural heritage analysis.
More from Multimodal
- One Japanese i2v prompt turns still images into paper-cut style motion graphics — Hailuo_AI · 2026-09-08
- Hunting for a mask + reference image inpainting workflow that doesn't sacrifice quality — NeoHisto · 2026-09-08
- Adobe Makes Premiere's AI Generators Workflow-Native With Generative Media — The Verge AI · 2026-09-08
- 8GB VRAM runs Flux and Wan 2.2 locally fine: three wrong settings, not the GPU, were the bottleneck — leonbuilds · 2026-09-08
- SuperSplat Editor 3.0 rebuilt on WebGPU, handles tens of millions of Gaussians — willeastcott · 2026-09-08
- Fixing broken text in AI slides: generate the design, strip the text, then let AI refill it — algo_diver · 2026-09-08