SceneCrafter: Controllable Multi-View Driving Scene Editing
Zehao Zhu, Yuliang Zou, Chiyu Max Jiang, Bo Sun, Vincent Casser, Xiukun Huang, Jiahao Wang, Zhenpei Yang, Ruiqi Gao, Leonidas J. Guibas, Mingxing Tan, Dragomir Anguelov
Abstract
Remove this car Add a car here Make the scene Snowy Change time to 10pm Figure 1. SceneCrafter is a versatile and dexterous editor for realistic 3D-consistent manipulation of driving scenes captured from multiple camera angles. It allows users to seamlessly insert or remove arbitrary objects in the foreground (second row) and modify global features like weather (third row) and time of day (fourth row), while preserving fine-grained details of scene layout and geometry.
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 37ffc132-ff51-4dcf-9e97-268e61daaf34Cited by top-tier papers2
- Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous DrivingJiahao Wang, Bo Sun, Yijing Bai, Vincent Casser et al.CVPR 2026 · 2 citations
- DrivePTS: A Progressive Learning Framework with Textual and Structural Enhancement for Driving Scene GenerationZhechao Wang, Yiming Zeng, Lufan Ma, Zeqing Fu et al.CVPR 2026 · 2 citations
Builds on37
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- 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
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
Related papers
- Unraveling the Effects of Synthetic Data on End-to-End Autonomous DrivingJunhao Ge, Zuhong Liu, Longteng Fan, Yifan Jiang et al.ICCV 2025 · 2 citations
- CCEdit: Creative and Controllable Video Editing via Diffusion ModelsRuoyu Feng, Wenming Weng, Yanhui Wang, Yuhui Yuan et al.CVPR 2024
- HorizonForge: Driving Scene Editing with Any Trajectories and Any VehiclesYifan Wang, Francesco Pittaluga, Zaid Tasneem, Chenyu You et al.CVPR 2026 · 3 citations
- WeatherEdit: Controllable Weather Editing with 4D Gaussian FieldChenghao Qian, Wenjing Li, Yuhu Guo, Gustav MarkkulaAAAI 2026 · 6 citations
- CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D DiffusionKai He, Chin-Hsuan Wu, Igor GilitschenskiCVPR 2025
