Moving beyond the traditional paradigms of "Thinking with Text" (e.g., Chain-of-Thought) and "Thinking with Images", we propose "Thinking with Video"—a new paradigm that unifies visual and textual ...
This repository contains code release for our CVPR 2025 paper "DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation". conda create -n di-pcg ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results