# MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability

arXiv: https://arxiv.org/abs/2407.19468 · HTML: https://mlsanity.com/paper/2407.19468/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 28 Jul 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion](https://mlsanity.com/paper/2307.01097/) (2023)
- [View Synthesis by Appearance Flow](https://mlsanity.com/paper/1605.03557/) (2016)
- [Street-View Image Generation from a Bird's-Eye View Layout](https://mlsanity.com/paper/2301.04634/) (2023)
- [BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout](https://mlsanity.com/paper/2308.01661/) (2023)
- [Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction](https://mlsanity.com/paper/2104.08277/) (2021)
- [Learning Aerial Image Segmentation from Online Maps](https://mlsanity.com/paper/1707.06879/) (2017)
- [A Parametric Top-View Representation of Complex Road Scenes](https://mlsanity.com/paper/1812.06152/) (2018)
- [Weakly But Deeply Supervised Occlusion-Reasoned Parametric Road Layouts](https://mlsanity.com/paper/2104.06730/) (2021)

## Built on by (most cited first, 7 of 7)

- [VideoPanda: Video Panoramic Diffusion with Multi-view Attention](https://mlsanity.com/paper/2504.11389/) (2025)
- [DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer](https://mlsanity.com/paper/2504.19614/) (2025)
- [OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving](https://mlsanity.com/paper/2512.14225/) (2025)
- [HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles](https://mlsanity.com/paper/2602.21333/) (2026)
- [AutoScape: Geometry-Consistent Long-Horizon Scene Generation](https://mlsanity.com/paper/2510.20726/) (2025)
- [DrivePTS: A Progressive Learning Framework with Textual and Structural Enhancement for Driving Scene Generation](https://mlsanity.com/paper/2602.22549/) (2026)
- [FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model](https://mlsanity.com/paper/2606.20110/) (2026)

## Abstract (arXiv)

This work aims to address the multi-view perspective RGB generation from text prompts given Bird-Eye-View(BEV) semantics. Unlike prior methods that neglect layout consistency, lack the ability to handle detailed text prompts, or are incapable of generalizing to unseen view points, MVPbev simultaneously generates cross-view consistent images of different perspective views with a two-stage design, allowing object-level control and novel view generation at test-time. Specifically, MVPbev firstly projects given BEV semantics to perspective view with camera parameters, empowering the model to generalize to unseen view points. Then we introduce a multi-view attention module where special initialization and de-noising processes are introduced to explicitly enforce local consistency among overlapping views w.r.t. cross-view homography. Last but not least, MVPbev further allows test-time instance-level controllability by refining a pre-trained text-to-image diffusion model. Our extensive experiments on NuScenes demonstrate that our method is capable of generating high-resolution photorealistic images from text descriptions with thousands of training samples, surpassing the state-of-the-art methods under various evaluation metrics. We further demonstrate the advances of our method in terms of generalizability and controllability with the help of novel evaluation metrics and comprehensive human analysis. Our code, data, and model can be found in urlhttps://github.com/kkaiwwana/MVPbev.