UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation

• URL: http://arxiv.org/abs/2411.19292v1
• Date: Thu, 28 Nov 2024 17:51:08 GMT
• Title: UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation
• Authors: Yichong Lu, Yichi Cai, Shangzhan Zhang, Hongyu Zhou, Haoji Hu, Huimin Yu, Andreas Geiger, Yiyi Liao,
• Abstract summary: Photorealistic 3D vehicle models with high controllability are essential for autonomous driving simulation and data augmentation. We introduce UrbanCAD, a framework that generates highly controllable and photorealistic 3D vehicle digital twins from a single urban image.
• Score: 46.47972242593905
• License:
• Abstract: Photorealistic 3D vehicle models with high controllability are essential for autonomous driving simulation and data augmentation. While handcrafted CAD models provide flexible controllability, free CAD libraries often lack the high-quality materials necessary for photorealistic rendering. Conversely, reconstructed 3D models offer high-fidelity rendering but lack controllability. In this work, we introduce UrbanCAD, a framework that pushes the frontier of the photorealism-controllability trade-off by generating highly controllable and photorealistic 3D vehicle digital twins from a single urban image and a collection of free 3D CAD models and handcrafted materials. These digital twins enable realistic 360-degree rendering, vehicle insertion, material transfer, relighting, and component manipulation such as opening doors and rolling down windows, supporting the construction of long-tail scenarios. To achieve this, we propose a novel pipeline that operates in a retrieval-optimization manner, adapting to observational data while preserving flexible controllability and fine-grained handcrafted details. Furthermore, given multi-view background perspective and fisheye images, we approximate environment lighting using fisheye images and reconstruct the background with 3DGS, enabling the photorealistic insertion of optimized CAD models into rendered novel view backgrounds. Experimental results demonstrate that UrbanCAD outperforms baselines based on reconstruction and retrieval in terms of photorealism. Additionally, we show that various perception models maintain their accuracy when evaluated on UrbanCAD with in-distribution configurations but degrade when applied to realistic out-of-distribution data generated by our method. This suggests that UrbanCAD is a significant advancement in creating photorealistic, safety-critical driving scenarios for downstream applications.

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)
• MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes [72.02827211293736]
  We introduce MagicDrive3D, a novel pipeline for controllable 3D street scene generation. Unlike previous methods that reconstruct before training the generative models, MagicDrive3D first trains a video generation model and then reconstructs from the generated data. Our results demonstrate the framework's superior performance, showcasing its potential for autonomous driving simulation and beyond.
  arXiv  Detail & Related papers  (2024-05-23T12:04:51Z)
• En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data [36.51674664590734]
  We present En3D, an enhanced izable scheme for high-qualityd 3D human avatars. Unlike previous works that rely on scarce 3D datasets or limited 2D collections with imbalance viewing angles and pose priors, our approach aims to develop a zero-shot 3D capable of producing 3D humans.
  arXiv  Detail & Related papers  (2024-01-02T12:06:31Z)
• DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image [34.47379913018661]
  We propose DiffCAD, the first weakly-supervised probabilistic approach to CAD retrieval and alignment from an RGB image. We formulate this as a conditional generative task, leveraging diffusion to learn implicit probabilistic models capturing the shape, pose, and scale of CAD objects in an image. Our approach is trained only on synthetic data, leveraging monocular depth and mask estimates to enable robust zero-shot adaptation to various real target domains.
  arXiv  Detail & Related papers  (2023-11-30T15:10:21Z)
• EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction [53.28220984270622]
  3D reconstruction methods should generate high-fidelity results with 3D consistency in real-time. Our method can reconstruct high-quality appearance and accurate mesh on both synthetic and real-world datasets. Our method can be trained in just 1-2 hours using a single GPU and run on mobile devices at over 40 FPS (Frames Per Second)
  arXiv  Detail & Related papers  (2023-11-16T11:30:56Z)
• GINA-3D: Learning to Generate Implicit Neural Assets in the Wild [38.51391650845503]
  GINA-3D is a generative model that uses real-world driving data from camera and LiDAR sensors to create 3D implicit neural assets of diverse vehicles and pedestrians. We construct a large-scale object-centric dataset containing over 1.2M images of vehicles and pedestrians. We demonstrate that it achieves state-of-the-art performance in quality and diversity for both generated images and geometries.
  arXiv  Detail & Related papers  (2023-04-04T23:41:20Z)
• 3D Data Augmentation for Driving Scenes on Camera [50.41413053812315]
  We propose a 3D data augmentation approach termed Drive-3DAug, aiming at augmenting the driving scenes on camera in the 3D space. We first utilize Neural Radiance Field (NeRF) to reconstruct the 3D models of background and foreground objects. Then, augmented driving scenes can be obtained by placing the 3D objects with adapted location and orientation at the pre-defined valid region of backgrounds.
  arXiv  Detail & Related papers  (2023-03-18T05:51:05Z)
• Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve [54.054575408582565]
  We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an image. We present Mask2CAD, which jointly detects objects in real-world images and for each detected object, optimize for the most similar CAD model and its pose. This produces a clean, lightweight representation of the objects in an image.
  arXiv  Detail & Related papers  (2020-07-26T00:08:37Z)
• CAD-Deform: Deformable Fitting of CAD Models to 3D Scans [30.451330075135076]
  We introduce CAD-Deform, a method which obtains more accurate CAD-to-scan fits by non-rigidly deforming retrieved CAD models. A series of experiments demonstrate that our method achieves significantly tighter scan-to-CAD fits, allowing a more accurate digital replica of the scanned real-world environment.
  arXiv  Detail & Related papers  (2020-07-23T12:30:20Z)
• Learning Neural Light Transport [28.9247002210861]
  We present an approach for learning light transport in static and dynamic 3D scenes using a neural network. We find that our model is able to produce photorealistic renderings of static and dynamic scenes.
  arXiv  Detail & Related papers  (2020-06-05T13:26:05Z)

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.