HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation
Wenqi Dong, Bangbang Yang, Zesong Yang, Yuan Li, Tao Hu, Hujun Bao, Yuewen Ma, Zhaopeng Cui
Abstract
Scene-level 3D generation represents a critical frontier in multimedia and computer graphics. While existing approaches have achieved encouraging progress, they still face challenges such as constrained object diversity and limited support for interactive editing. In this paper, we present HiScene, a novel hierarchical framework that bridges the gap between 2D image generation and 3D object generation and delivers high-fidelity scenes with compositional identities and aesthetic scene content. Our key insight is treating scenes as hierarchical ''objects'' under isometric views, where a room functions as a complex object that can be further decomposed into manipulatable items. This hierarchical approach enables us to generate 3D content that aligns with 2D representations while maintaining compositional structure. To ensure completeness and spatial alignment of each decomposed instance, we develop a video-diffusion-based amodal completion technique that effectively handles occlusions and shadows between objects, and introduce shape prior injection to ensure spatial coherence within the scene. Experimental results demonstrate that our method produces more natural object arrangements and complete object instances suitable for interactive applications, while maintaining physical plausibility and alignment with user inputs.
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 80d9e871-7cc8-400b-9da6-5cec4c1701eeCited by top-tier papers6
- WorldGen: From Text to Traversable and Interactive 3D WorldsDilin Wang, Hyunyoung Jung, Tom Monnier, Kihyuk Sohn et al.CVPR 2026 · 24 citations
- WorldGrow: Generating Infinite 3D WorldSikuang Li, Chen Yang, Jiemin Fang, Taoran Yi et al.AAAI 2026 · 10 citations
- PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene ArrangementYian Wang, Han Yang, Minghao Guo, Xiaowen Qiu et al.ICLR 2026 · 10 citations
- CUPID: Generative 3D Reconstruction via Joint Object and Pose ModelingBinbin Huang, Haobin Duan, Yiqun Zhao, Zibo Zhao et al.CVPR 2026 · 8 citations
- MorphAny3D: Unleashing the Power of Structured Latent in 3D MorphingXiaokun Sun, Zeyu Cai, Hao Tang, Ying Tai et al.CVPR 2026 · 5 citations
Builds on56
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- 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
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann et al.ICLR 2024 · 4,569 citations
Related papers
- 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single ImageZe-Xin Yin, Liu Liu, Xinjie wang, Wei Sui et al.CVPR 2026 · 10 citations
- HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene GenerationBin Zang, Wenting Zheng, Xiaoliang Luo, Zhiyuan Fang et al.ICML 2026
- DiffInDScene: Diffusion-Based High-Quality 3D Indoor Scene GenerationXiaoliang Ju, Zhaoyang Huang, Yijiin Li, Guofeng Zhang et al.CVPR 2024
- SceneGenesis: 3D Scene Synthesis via Semantic Structural Priors and Mesh-Guided Video-Geometry FusionYueming Zhao, Hongyu Yang, Di HuangAAAI 2026
- DiffuScene: Denoising Diffusion Models for Generative Indoor Scene SynthesisJiapeng Tang, Yinyu Nie, Lev Markhasin, Angela Dai et al.CVPR 2024 · 62 citations
