Generative Blocks World: Moving Things Around in Pictures
Vaibhav Vavilala, Seemandhar Jain, Rahul Vasanth, David Forsyth, Anand Bhattad
Abstract
We describe Generative Blocks World to interact with the scene of a generated image by manipulating simple geometric abstractions. Our method represents scenes as assemblies of convex 3D primitives, and the same scene can be represented by different numbers of primitives, allowing an editor to move either whole structures or small details. Once the scene geometry has been edited, the image is generated by a flow-based method, which is conditioned on depth and a texture hint. Our texture hint takes into account the modified 3D primitives, exceeding the texture-consistency provided by existing techniques. These texture hints (a) allow accurate object and camera moves and (b) preserve the identity of objects. Our experiments demonstrate that our approach outperforms prior works in visual fidelity, editability, and compositional generalization.
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 papers1
Ask how each one uses itBuilds on32
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- Scaling Rectified Flow Transformers for High-Resolution Image SynthesisPatrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari et al.ICML 2024 · 3,620 citations
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao et al.NeurIPS 2024 · 2,305 citations
Related papers
- Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel FlowShimin Hu, Yuanyi Wei, Fei Zha, Yudong Guo et al.CVPR 2026 · 7 citations
- SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image GenerationVaibhav Agrawal, Rishubh Parihar, Pradhaan Bhat, Ravi Kiran Sarvadevabhatla et al.CVPR 2026 · 5 citations
- Vinedresser3D: Towards Agentic Text-guided 3D EditingYankuan Chi, Xiang Li, Zixuan Huang, James M.CVPR 2026
- Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3DKarran Pandey, Paul Guerrero, Matheus Gadelha, Yannick Hold-Geoffroy et al.CVPR 2024 · 19 citations
- Differentiable Blocks World: Qualitative 3D Decomposition by Rendering PrimitivesTom Monnier, Jake Austin, Angjoo Kanazawa, Alexei A. Efros et al.NeurIPS 2023 · 50 citations
