AI tools for Matting

WeVisOne-VL is a vision-language model that handles fine-grained visual perception from individual objects down to pixels. A Qwen3-VL backbone predicts structured coordinate tok

Lucida is an open image matting and background removal model focused on hard cases that general-purpose removers often miss. It is tuned for semi-transparent objects, camouflage

UniVidX is a unified multimodal framework for versatile video generation across many input and output modalities. Rather than training a separate video diffusion model for each

VideoMaMa, or Video Mask-to-Matte Model, is an innovative approach to video matting that transforms coarse segmentation masks into highly precise alpha mattes without requiring