Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion
Kaizhe Hu, Zihang Rui, Yao He, Yuyao Liu, Pu Hua, Huazhe Xu
2025Year
1Top-tier citations
Abstract
The tree of Stem-OB inversion is composed of different objects progressively inverted through a diffusion inversion process. Moving downward alone the tree's branches, objects of different textures, appearances, and categories gradually get closer, eventually converging into the same root of Gaussian noise, where they are completely indistinguishable. Right: Real-world tasks success rate, where Stem-OB showcases a significant improvement.
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.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 2bb897df-636c-4c5a-b2e0-85394c025ee9Cited by top-tier papers1
Ask how each one uses itBuilds on21
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Scaling Rectified Flow Transformers for High-Resolution Image SynthesisPatrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari et al.ICML 2024 · 3,620 citations
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential EquationsChenlin Meng, Yutong He, Yang Song, Jiaming Song et al.ICLR 2022 · 2,128 citations
Related papers
- CObL: Toward Zero-Shot Ordinal Layering Without User PromptingAneel Damaraju, Dean Hazineh, Todd E. ZicklerICCV 2025
- SVDTree: Semantic Voxel Diffusion for Single Image Tree ReconstructionYuan Li, Zhihao Liu, Bedrich Benes, Xiaopeng Zhang et al.CVPR 2024
- Rethinking Visual Rearrangement from A Diffusion PerspectiveTianliang Qi, Xinhang Song, Yuyi Liu, Shuqiang JiangCVPR 2026
- IMAGINE: Image Synthesis by Image-Guided Model InversionPei Wang, Yijun Li, Krishna Kumar Singh, Jingwan Lu et al.CVPR 2021
- An Edit Friendly DDPM Noise Space: Inversion and ManipulationsInbar Huberman-Spiegelglas, Vladimir Kulikov, Tomer MichaeliCVPR 2024
