ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration

• URL: http://arxiv.org/abs/2411.19548v1
• Date: Fri, 29 Nov 2024 08:47:46 GMT
• Title: ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
• Authors: Chaojun Ni, Guosheng Zhao, Xiaofeng Wang, Zheng Zhu, Wenkang Qin, Guan Huang, Chen Liu, Yuyin Chen, Yida Wang, Xueyang Zhang, Yifei Zhan, Kun Zhan, Peng Jia, Xianpeng Lang, Xingang Wang, Wenjun Mei,
• Abstract summary: ReconDreamer enhances driving scene reconstruction through incremental integration of world model knowledge. To the best of our knowledge, ReconDreamer is the first method to effectively render in large maneuvers.
• Score: 30.755679955159504
• License:
• Abstract: Closed-loop simulation is crucial for end-to-end autonomous driving. Existing sensor simulation methods (e.g., NeRF and 3DGS) reconstruct driving scenes based on conditions that closely mirror training data distributions. However, these methods struggle with rendering novel trajectories, such as lane changes. Recent works have demonstrated that integrating world model knowledge alleviates these issues. Despite their efficiency, these approaches still encounter difficulties in the accurate representation of more complex maneuvers, with multi-lane shifts being a notable example. Therefore, we introduce ReconDreamer, which enhances driving scene reconstruction through incremental integration of world model knowledge. Specifically, DriveRestorer is proposed to mitigate artifacts via online restoration. This is complemented by a progressive data update strategy designed to ensure high-quality rendering for more complex maneuvers. To the best of our knowledge, ReconDreamer is the first method to effectively render in large maneuvers. Experimental results demonstrate that ReconDreamer outperforms Street Gaussians in the NTA-IoU, NTL-IoU, and FID, with relative improvements by 24.87%, 6.72%, and 29.97%. Furthermore, ReconDreamer surpasses DriveDreamer4D with PVG during large maneuver rendering, as verified by a relative improvement of 195.87% in the NTA-IoU metric and a comprehensive user study.

Related papers

• Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles [81.29018359825872]
  This paper consolidates a set of good practices to finetune large pretrained models for a real-world task. Specifically, we develop several strategies to account for discrepancies between the synthetic data and real driving data. Our insights lead to effective finetuning that results in a $68.8%$ reduction in FID for novel view synthesis over prior arts.
  arXiv  Detail & Related papers  (2024-12-19T03:39:13Z)
• DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving [83.27075316161086]
  Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. We introduce the Large 4D Gaussian Reconstruction Model (DrivingRecon), a generalizable driving scene reconstruction model. We show that DrivingRecon significantly improves scene reconstruction quality and novel view synthesis compared to existing methods.
  arXiv  Detail & Related papers  (2024-12-12T08:10:31Z)
• DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation [32.19534057884047]
  We introduce DriveDreamer4D, which enhances 4D driving scene representation leveraging world model priors. To our knowledge, DriveDreamer4D is the first to utilize video generation models for improving 4D reconstruction in driving scenarios.
  arXiv  Detail & Related papers  (2024-10-17T14:07:46Z)
• Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models [60.87795376541144]
  A world model is a neural network capable of predicting an agent's next state given past states and actions. During end-to-end training, our policy learns how to recover from errors by aligning with states observed in human demonstrations. We present qualitative and quantitative results, demonstrating significant improvements upon prior state of the art in closed-loop testing.
  arXiv  Detail & Related papers  (2024-09-25T06:48:25Z)
• CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation [44.83732884335725]
  Sensor simulation involves modeling traffic participants, such as vehicles, with high quality appearance and articulated geometry. Current reconstruction approaches struggle on in-the-wild sensor data, due to its sparsity and noise. We present CADSim, which combines part-aware object-class priors via a small set of CAD models with differentiable rendering to automatically reconstruct vehicle geometry.
  arXiv  Detail & Related papers  (2023-11-02T17:56:59Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning [84.30765628008207]
  We propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning. Our method outperforms the current state-of-the-art methods by a large margin on both benchmarks.
  arXiv  Detail & Related papers  (2021-06-08T07:37:37Z)
• There and Back Again: Learning to Simulate Radar Data for Real-World Applications [21.995474023869388]
  We learn a radar sensor model capable of synthesising faithful radar observations based on simulated elevation maps. We adopt an adversarial approach to learning a forward sensor model from unaligned radar examples. We demonstrate the efficacy of our approach by evaluating a down-stream segmentation model trained purely on simulated data in a real-world deployment.
  arXiv  Detail & Related papers  (2020-11-29T15:49:23Z)
• Recovering and Simulating Pedestrians in the Wild [81.38135735146015]
  We propose to recover the shape and motion of pedestrians from sensor readings captured in the wild by a self-driving car driving around. We incorporate the reconstructed pedestrian assets bank in a realistic 3D simulation system. We show that the simulated LiDAR data can be used to significantly reduce the amount of real-world data required for visual perception tasks.
  arXiv  Detail & Related papers  (2020-11-16T17:16:32Z)
• Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles [11.180588185127892]
  Supervised learning algorithms can generalize to new environments by training on a large amount of labeled data. It can be often impractical or cost-prohibitive to obtain sufficient data for each new environment. We propose a meta reinforcement learning (MRL) method to improve the agent's generalization capabilities.
  arXiv  Detail & Related papers  (2020-08-28T02:57:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.