# Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving

arXiv: https://arxiv.org/abs/2606.10656 · HTML: https://mlsanity.com/paper/2606.10656/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 60 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 30 of 56)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [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)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [Splatter Image: Ultra-Fast Single-View 3D Reconstruction](https://mlsanity.com/paper/2312.13150/) (2023)
- [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views](https://mlsanity.com/paper/2505.23716/) (2025)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation](https://mlsanity.com/paper/2503.19755/) (2025)
- [OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model](https://mlsanity.com/paper/2503.23463/) (2025)
- [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)
- [Video World Models with Long-term Spatial Memory](https://mlsanity.com/paper/2506.05284/) (2025)

## Built on by (most cited first, 1 of 1)

- [4DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian Splatting](https://mlsanity.com/paper/2608.25956/) (2026)

## Abstract (arXiv)

Forecasting the future evolution of dynamic scenes is crucial in autonomous driving. However, existing feed-forward paradigms are primarily designed for interpolation. When extended to future extrapolation, they suffer from ghosting artifacts under large displacements and are constrained by simplified motion assumptions or strict future priors. To overcome these challenges, we propose Envision4D, a fully self-supervised feed-forward framework for pose-free future extrapolation. Specifically, we introduce a Future Pose Prediction module that infers future camera parameters via an iterative denoising process. Furthermore, to capture non-linear dynamics, we propose In-layer Temporal Attention and employ Conditioned Motion Lifting, which transforms the highly uncertain extrapolation process into robust relational mappings. Finally, a Progressive Training Strategy is utilized to stabilize unsupervised motion learning against error accumulation. Extensive experiments demonstrate that Envision4D achieves state-of-the-art performance, significantly outperforming existing methods in future view synthesis.