PhyS-EdiT: Physics-aware Semantic Image Editing with Text Description
Ziqi Cai, Shuchen Weng, Yifei Xia, Boxin Shi
2025Year
2Top-tier citations
Abstract
Lighting Metallic Roughness Transparency Albedo Semantic ↑ ↓ ↑ ↓ Figure 1. Illustration of PhyS-EdiT's capabilities in disentangled control over lighting, material properties, and high-level semantics. The symbols ↑ and ↓ indicate an increase and a decrease in property value, respectively. Rows show variations in lighting environments, while columns show precise adjustments to individual material properties. The rightmost column presents a semantic edit with the prompt: "The knight is holding the sword.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers2
- Lighting-grounded Video Generation with Renderer-based Agent ReasoningZiqi Cai, Taoyu Yang, Zheng Chang, Si Li et al.CVPR 2026 · 3 citations
- TexEditor: Structure-Preserving Text-Driven Texture EditingBo Zhao, Yihang Liu, Chenfeng Zhang, Huan Yang et al.ICML 2026 · 1 citation
Builds on28
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
Related papers
- Alchemist: Parametric Control of Material Properties with Diffusion ModelsPrafull Sharma, Varun Jampani, Yuanzhen Li, Xuhui Jia et al.CVPR 2024 · 16 citations
- MARBLE: Material Recomposition and Blending in CLIP-SpaceTa Ying Cheng, Prafull Sharma, Mark Boss, Varun JampaniCVPR 2025
- V-RGBX: Video Editing with Accurate Controls over Intrinsic PropertiesYe Fang, Tong Wu, Valentin Deschaintre, Duygu Ceylan et al.CVPR 2026 · 5 citations
- LightMover: Generative Light Movement with Color and Intensity ControlsGengze Zhou, Tianyu Wang, Soo Ye Kim, ZHIXIN SHU et al.CVPR 2026 · 1 citation
- PBR3DGen: A VLM-Guided Mesh Generation with High-Quality PBR TextureXiaokang Wei, Bowen Zhang, Xianghui Yang, Yuxuan Wang et al.AAAI 2026 · 1 citation
