Reproduce “InsTex: Indoor Scenes Stylized Texture Synthesis” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yunfan Zhang, Zhiwei Xiong, Zhiqi Shen, Guosheng Lin, Hao Wang, Nicolas Vun
InsTex textures indoor 3D scenes by decomposing them into objects, generating depth-guided textures from multiple views, and refining them with shared room-style guidance. The authors evaluate it on 10 3D-FRONT scenes using text prompts. Its average CLIP score is 24.18, compared with 22.18 for SceneTex, indicating stronger prompt-image alignment under this evaluation, not generalization beyond it.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.