Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles

• URL: http://arxiv.org/abs/2412.14494v1
• Date: Thu, 19 Dec 2024 03:39:13 GMT
• Title: Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles
• Authors: Chuang Lin, Bingbing Zhuang, Shanlin Sun, Ziyu Jiang, Jianfei Cai, Manmohan Chandraker,
• Abstract summary: 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.
• Score: 81.29018359825872
• License:
• Abstract: The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the synthetic nature of such 3D data, their performance drops significantly when applied to real-world images. This paper consolidates a set of good practices to finetune large pretrained models for a real-world task -- harvesting vehicle assets for autonomous driving applications. To this end, we delve into the discrepancies between the synthetic data and real driving data, then develop several strategies to account for them properly. Specifically, we start with a virtual camera rotation of real images to ensure geometric alignment with synthetic data and consistency with the pose manifold defined by pretrained models. We also identify important design choices in object-centric data curation to account for varying object distances in real driving scenes -- learn across varying object scales with fixed camera focal length. Further, we perform occlusion-aware training in latent spaces to account for ubiquitous occlusions in real data, and handle large viewpoint changes by leveraging a symmetric prior. Our insights lead to effective finetuning that results in a $68.8\%$ reduction in FID for novel view synthesis over prior arts.

Related papers

• SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs [34.41011015930057]
  SyntheOcc addresses the challenge of how to efficiently encode 3D geometric information as conditional input to a 2D diffusion model. Our approach innovatively incorporates 3D semantic multi-plane images (MPIs) to provide comprehensive and spatially aligned 3D scene descriptions.
  arXiv  Detail & Related papers  (2024-10-01T02:29:24Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• Augmented Reality based Simulated Data (ARSim) with multi-view consistency for AV perception networks [47.07188762367792]
  We present ARSim, a framework designed to enhance real multi-view image data with 3D synthetic objects of interest. We construct a simplified virtual scene using real data and strategically place 3D synthetic assets within it. The resulting augmented multi-view consistent dataset is used to train a multi-camera perception network for autonomous vehicles.
  arXiv  Detail & Related papers  (2024-03-22T17:49:11Z)
• Robust Category-Level 3D Pose Estimation from Synthetic Data [17.247607850702558]
  We introduce SyntheticP3D, a new synthetic dataset for object pose estimation generated from CAD models. We propose a novel approach (CC3D) for training neural mesh models that perform pose estimation via inverse rendering.
  arXiv  Detail & Related papers  (2023-05-25T14:56:03Z)
• A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation [42.2398858786125]
  Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. The uncontrollable data collection process produces non-IID training and test data, where undesired duplication may exist. To circumvent them, an alternative is to generate synthetic data via 3D rendering with domain randomization.
  arXiv  Detail & Related papers  (2023-03-16T09:03:52Z)
• Synthetic Image Data for Deep Learning [0.294944680995069]
  Realistic synthetic image data rendered from 3D models can be used to augment image sets and train image classification semantic segmentation models. We show how high quality physically-based rendering and domain randomization can efficiently create a large synthetic dataset based on production 3D CAD models of a real vehicle.
  arXiv  Detail & Related papers  (2022-12-12T20:28:13Z)
• RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection [138.2892824662943]
  A promising solution is to make better use of the synthetic dataset, which consists of CAD object models, to boost the learning on real datasets. Recent work on 3D pre-training exhibits failure when transfer features learned on synthetic objects to other real-world applications. In this work, we put forward a new method called RandomRooms to accomplish this objective.
  arXiv  Detail & Related papers  (2021-08-17T17:56:12Z)
• Secrets of 3D Implicit Object Shape Reconstruction in the Wild [92.5554695397653]
  Reconstructing high-fidelity 3D objects from sparse, partial observation is crucial for various applications in computer vision, robotics, and graphics. Recent neural implicit modeling methods show promising results on synthetic or dense datasets. But, they perform poorly on real-world data that is sparse and noisy. This paper analyzes the root cause of such deficient performance of a popular neural implicit model.
  arXiv  Detail & Related papers  (2021-01-18T03:24:48Z)
• Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition [67.9464567157846]
  We propose an autoencoder for joint generation of realistic images from synthetic 3D models while simultaneously decomposing real images into their intrinsic shape and appearance properties. Our experiments confirm that a joint treatment of rendering and decomposition is indeed beneficial and that our approach outperforms state-of-the-art image-to-image translation baselines both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2020-06-29T12:53:58Z)
• Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction [118.21363599332493]
  We present a method to leverage photometric consistency across time when annotations are only available for a sparse subset of frames in a video. Our model is trained end-to-end on color images to jointly reconstruct hands and objects in 3D by inferring their poses. We achieve state-of-the-art results on 3D hand-object reconstruction benchmarks and demonstrate that our approach allows us to improve the pose estimation accuracy.
  arXiv  Detail & Related papers  (2020-04-28T12:03:14Z)

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.