# VisionNVS: Self-Supervised Inpainting for Novel View Synthesis under the Virtual-Shift Paradigm

arXiv: https://arxiv.org/abs/2603.17382 · HTML: https://mlsanity.com/paper/2603.17382/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Flow Matching Guide and Code](https://mlsanity.com/paper/2412.06264/) (2024)
- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision](https://mlsanity.com/paper/2311.02077/) (2023)
- [OmniRe: Omni Urban Scene Reconstruction](https://mlsanity.com/paper/2408.16760/) (2024)
- [Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering](https://mlsanity.com/paper/2311.18561/) (2023)
- [textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Driving](https://mlsanity.com/paper/2405.20323/) (2024)
- [3D Gaussian as a New Era: A Survey](https://mlsanity.com/paper/2402.07181/) (2024)
- [3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities](https://mlsanity.com/paper/2407.17418/) (2024)
- [DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input](https://mlsanity.com/paper/2409.12753/) (2024)
- [FreeVS: Generative View Synthesis on Free Driving Trajectory](https://mlsanity.com/paper/2410.18079/) (2024)
- [DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation](https://mlsanity.com/paper/2503.15208/) (2025)
- [RemoteSAM: Towards Segment Anything for Earth Observation](https://mlsanity.com/paper/2505.18022/) (2025)
- [RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow](https://mlsanity.com/paper/2507.19280/) (2025)
- [Neural Radiance Field in Autonomous Driving: A Survey](https://mlsanity.com/paper/2404.13816/) (2024)
- [EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting](https://mlsanity.com/paper/2410.15392/) (2024)
- [Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories](https://mlsanity.com/paper/2412.10078/) (2024)

## Abstract (arXiv)

A fundamental bottleneck in Novel View Synthesis (NVS) for autonomous driving is the inherent supervision gap on novel trajectories: models are tasked with synthesizing unseen views during inference, yet lack ground truth images for these shifted poses during training. In this paper, we propose VisionNVS, a camera-only framework that fundamentally reformulates view synthesis from an ill-posed extrapolation problem into a self-supervised inpainting task. By introducing a ``Virtual-Shift'' strategy, we use monocular depth proxies to simulate occlusion patterns and map them onto the original view. This paradigm shift allows the use of raw, recorded images as pixel-perfect supervision, effectively eliminating the domain gap inherent in previous approaches. Furthermore, we address spatial consistency through a Pseudo-3D Seam Synthesis strategy, which integrates visual data from adjacent cameras during training to explicitly model real-world photometric discrepancies and calibration errors. Experiments demonstrate that VisionNVS achieves superior geometric fidelity and visual quality compared to LiDAR-dependent baselines, offering a robust solution for scalable driving simulation.