Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
AssetDropperassetdropper.github.io · Low evidenceAssetDropper is a generative framework from Hong Kong University of Science and Technology (Guangzhou), Peking University, The University of Hong Kong, and Hong Kong University of Science and Technology that extracts standardized assets from user-specified regions of reference images. It uses diffusion models with reward-driven optimization to handle perspective distortion and occlusion, enabling downstream applications like 2D mockup creation and 3D model texturing.
Parse Score