Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding

• URL: http://arxiv.org/abs/2212.05040v3
• Date: Fri, 7 Jun 2024 16:26:05 GMT
• Title: Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding
• Authors: Jay Bhanushali, Manivannan Muniyandi, Praneeth Chakravarthula,
• Abstract summary: Cross-domain inference technique learns from synthetic data to estimate depth and normals for in-the-wild omnidirectional 3D scenes. We introduce UBotNet, an architecture that combines UNet and Bottleneck Transformer elements to predict consistent scene normals and depth. We validate cross-domain synthetic-to-real depth and normal estimation on real outdoor images using UBotNet trained solely on our synthetic OmniHorizon dataset.
• Score: 5.561698802097603
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We present a cross-domain inference technique that learns from synthetic data to estimate depth and normals for in-the-wild omnidirectional 3D scenes encountered in real-world uncontrolled settings. To this end, we introduce UBotNet, an architecture that combines UNet and Bottleneck Transformer elements to predict consistent scene normals and depth. We also introduce the OmniHorizon synthetic dataset containing 24,335 omnidirectional images that represent a wide variety of outdoor environments, including buildings, streets, and diverse vegetation. This dataset is generated from expansive, lifelike virtual spaces and encompasses dynamic scene elements, such as changing lighting conditions, different times of day, pedestrians, and vehicles. Our experiments show that UBotNet achieves significantly improved accuracy in depth estimation and normal estimation compared to existing models. Lastly, we validate cross-domain synthetic-to-real depth and normal estimation on real outdoor images using UBotNet trained solely on our synthetic OmniHorizon dataset, demonstrating the potential of both the synthetic dataset and the proposed network for real-world scene understanding applications.

Related papers

• 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)
• Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation? [61.234412062595155]
  We present ANYU, a new virtually augmented version of the NYU depth v2 dataset, designed for monocular depth estimation. In contrast to the well-known approach where full 3D scenes of a virtual world are utilized to generate artificial datasets, ANYU was created by incorporating RGB-D representations of virtual reality objects. We show that ANYU improves the monocular depth estimation performance and generalization of deep neural networks with considerably different architectures.
  arXiv  Detail & Related papers  (2024-04-15T05:44:03Z)
• 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)
• CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion [83.30168660888913]
  We present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model.
  arXiv  Detail & Related papers  (2023-05-25T17:39:13Z)
• Semi-Perspective Decoupled Heatmaps for 3D Robot Pose Estimation from Depth Maps [66.24554680709417]
  Knowing the exact 3D location of workers and robots in a collaborative environment enables several real applications. We propose a non-invasive framework based on depth devices and deep neural networks to estimate the 3D pose of robots from an external camera.
  arXiv  Detail & Related papers  (2022-07-06T08:52:12Z)
• Leveraging Deepfakes to Close the Domain Gap between Real and Synthetic Images in Facial Capture Pipelines [8.366597450893456]
  We propose an end-to-end pipeline for building and tracking 3D facial models from personalized in-the-wild video data. We present a method for automatic data curation and retrieval based on a hierarchical clustering framework typical of collision algorithms in traditional computer graphics pipelines. We outline how we train a motion capture regressor, leveraging the aforementioned techniques to avoid the need for real-world ground truth data.
  arXiv  Detail & Related papers  (2022-04-22T15:09:49Z)
• Towards 3D Scene Understanding by Referring Synthetic Models [65.74211112607315]
  Methods typically alleviate on-extensive annotations on real scene scans. We explore how synthetic models rely on real scene categories of synthetic features to a unified feature space. Experiments show that our method achieves the average mAP of 46.08% on the ScanNet S3DIS dataset and 55.49% by learning datasets.
  arXiv  Detail & Related papers  (2022-03-20T13:06:15Z)
• STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset [6.812704277866377]
  We introduce a synthetic aerial photogrammetry point clouds generation pipeline. Unlike generating synthetic data in virtual games, the proposed pipeline simulates the reconstruction process of the real environment. We present a richly-annotated synthetic 3D aerial photogrammetry point cloud dataset.
  arXiv  Detail & Related papers  (2022-03-17T03:50:40Z)
• OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems [88.41004332322788]
  We present an omnidirectional localization and dense mapping system for a wide-baseline multiview stereo setup with ultra-wide field-of-view (FOV) fisheye cameras. For more practical and accurate reconstruction, we first introduce improved and light-weighted deep neural networks for the omnidirectional depth estimation. We integrate our omnidirectional depth estimates into the visual odometry (VO) and add a loop closing module for global consistency.
  arXiv  Detail & Related papers  (2020-03-18T05:52:10Z)
• Virtual to Real adaptation of Pedestrian Detectors [9.432150710329607]
  ViPeD is a new synthetically generated set of images collected with the graphical engine of the video game GTA V - Grand Theft Auto V. We propose two different Domain Adaptation techniques suitable for the pedestrian detection task, but possibly applicable to general object detection. Experiments show that the network trained with ViPeD can generalize over unseen real-world scenarios better than the detector trained over real-world data.
  arXiv  Detail & Related papers  (2020-01-09T14:50:11Z)

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.