# UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation

arXiv: https://arxiv.org/abs/2610.03473 · HTML: https://mlsanity.com/paper/2610.03473/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 30 of 32)

- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023)
- [DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation](https://mlsanity.com/paper/2403.06845/) (2024)
- [SimVP: Simpler yet Better Video Prediction](https://mlsanity.com/paper/2206.05099/) (2022)
- [ADriver-I: A General World Model for Autonomous Driving](https://mlsanity.com/paper/2311.13549/) (2023)
- [Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction](https://mlsanity.com/paper/2102.09320/) (2021)
- [Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2206.12126/) (2022)
- [GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control](https://mlsanity.com/paper/2412.11198/) (2024)
- [Learning Dense and Continuous Optical Flow from an Event Camera](https://mlsanity.com/paper/2211.09078/) (2022)
- [Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2)](https://mlsanity.com/paper/2402.16720/) (2024)
- [Dense Continuous-Time Optical Flow from Events and Frames](https://mlsanity.com/paper/2203.13674/) (2022)
- [DINO-Foresight: Looking into the Future with DINO](https://mlsanity.com/paper/2412.11673/) (2024)
- [SRFNet: Monocular Depth Estimation with Fine-grained Structure via Spatial Reliability-oriented Fusion of Frames and Events](https://mlsanity.com/paper/2309.12842/) (2023)
- [Seeing Through Pixel Motion: Learning Obstacle Avoidance from Optical Flow with One Camera](https://mlsanity.com/paper/2411.04413/) (2024)
- [E-Motion: Future Motion Simulation via Event Sequence Diffusion](https://mlsanity.com/paper/2410.08649/) (2024)
- [Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers](https://mlsanity.com/paper/2501.08303/) (2025)
- [PCDepth: Pattern-based Complementary Learning for Monocular Depth Estimation by Best of Both Worlds](https://mlsanity.com/paper/2402.18925/) (2024)
- [Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation](https://mlsanity.com/paper/2501.00838/) (2025)
- [UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block](https://mlsanity.com/paper/2507.19948/) (2025)
- [Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes](https://mlsanity.com/paper/2510.10577/) (2025)

## Abstract (arXiv)

We propose UniDynamics, a diffusion-based framework for future 4D dynamic scenes (RGB, depth, and optical flow) generation from a single event-RGB pair, without requiring long histories or control priors as in existing methods, while explicitly modeling future motion fields. The core idea is to leverage event streams to offer an alternative motion prior for single-RGB extrapolation, and to enforce geometric and motion constraints throughout generation via multimodal modeling. Specifically, we design an Event Latent Enhancement (ELE) module to align and enhance event latents into diffusion-injectable conditioning features, providing robust initial motion priors and reliable texture/structure cues. We further introduce a Perceptual Dynamics Space (PDS) embedded in the multi-scale U-Net, which decouples and adaptively interacts depth and flow while continuously feeding back constraints to appearance features, improving geometric-motion consistency for physically plausible and spatiotemporally coherent prediction. Experiments on VKitti2 and DSEC demonstrate state-of-the-art performance, producing high-quality, temporally coherent, and 4D-consistent future predictions, especially under challenging high-speed motion blur.