3D Scene Generation

Follow this topic Ask about this topic

3D scene generation studies how to turn prompts and visual observations into environments with coherent layouts, geometry, appearance, and sometimes motion or interaction. Methods range from procedural rules and language-model agents to diffusion, flow-matching, and autoregressive models that generate meshes, Gaussian splats, voxels, or occupancy representations. Work targets indoor design, large-scale worlds, driving scenes, and simulation for robotics, using constraints, rendering feedback, and physics checks to improve control and usability. A central challenge is balancing visual realism and scalable generation with consistent geometry, physical plausibility, editability, and reliable evaluation.

Latest papers

191 papers25 papers in the last four weeks, up 39% on the four weeks before. 0.1% of all new papers.

DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles
Feb 17, 2026Rong Fu, Jiekai Wu, Yang Li +33D Scene Generation 3D Gaussian Splatting
Independent Researcher
SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-Turn RL
Feb 10, 2026Yang Zhao, Shizhao Sun, Meisheng Zhang +33D Scene Generation Indoor Scene Generation
Shanghai Jiao Tong University, Shanghai, China · Microsoft Research Asia, Beijing, China · Peking University, Beijing, China +1
Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation
Dec 4, 2025Yanran Zhang, Ziyi Wang, Wenzhao Zheng +3Video Diffusion Models 3D Scene Generation
Department of Automation, Tsinghua University, China · GigaAI
TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation
Dec 1, 2025Ziqian Wang, Yonghao He, Licheng Yang +6Robotic Data Collection Robotics Simulation
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China · D-Robotics, Beijing, China +2
GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation
Nov 28, 2025Yuhao Wan, Lijuan Liu, Jingzhi Zhou +6Video Diffusion Models 3D Scene Generation
1VCIP & AAIS, Nankai University · 2ByteDance Inc. · 3Renmin University of China +2
LaGen: Towards Autoregressive LiDAR Scene Generation
Nov 26, 2025Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang +73D Scene Generation Autoregressive Generation
University of Science and Technology of China, Hefei, Anhui 230026, China · Shanghai Innovation Institute, Shanghai 200231, China · Fudan University, Shanghai 200433, China +1
Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagery
Nov 14, 2025Xinliang Wang, Yijie Kang, Zhenyu Wu +13D Asset Generation 3D Scene Generation
KE Holdings Inc., Beijing, China
Apples on the Table? Evaluating Text-Guided 3D Scene Synthesis via Fine-Grained Constraint Verification
Nov 4, 2025Minseok Kang, Dongwook Choi, Gyeom Hwangbo +33D Spatial Reasoning 3D Scene Generation
Yonsei University
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Oct 17, 2025Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai +63D Reconstruction 3D Scene Generation
National Yang Ming Chiao Tung University · UIUC · University of Zaragoza +1
MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusion
Aug 21, 2025Xuyang Chen, Zhijun Zhai, Kaixuan Zhou +103D Scene Generation Multi-View Image Synthesis
Huawei Hilbert Research Center · Technical University of Munich, Munich, Germany · Wuhan University, Wuhan, China +1
3D Software Synthesis Driven by Constraint-Expressive Intermediate Representation
Jul 24, 2025Shuqing Li, Anson Y. Lam, Yun Peng +2Program Synthesis 3D Scene Generation
The Chinese University of Hong Kong Hong Kong, China · Renmin University of China Beijing, China

Feb 17, 2026J/K move · Enter open · S save

DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles

Rong Fu, Jiekai Wu, Yang Li, Xiaowen Ma+2

Independent Researcher

3D Scene Generation 3D Gaussian Splatting Procedural Content Generation Sparse-View 3D Reconstruction Active View Selection

Open paper AskPDF arXiv

The emergence of 3D Gaussian Splatting has fundamentally redefined the capabilities of photorealistic neural rendering by enabling high-throughput synthesis of complex environments. While procedural methods like Wang Tiles have recently been integrated to facilitate the generation of expansive landscapes, these systems typically remain constrained by a reliance on densely sampled exemplar reconstructions. We present DAV-GSWT, a data-efficient framework that leverages diffusion priors and active view sampling to synthesize high-fidelity Gaussian Splatting Wang Tiles from minimal input observations. By integrating a hierarchical uncertainty quantification mechanism with generative diffusion models, our approach autonomously identifies the most informative viewpoints while hallucinating missing structural details to ensure seamless tile transitions. Experimental results indicate that our system significantly reduces the required data volume while maintaining the visual integrity and interactive performance necessary for large-scale virtual environments.