NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images

• URL: http://arxiv.org/abs/2402.18196v2
• Date: Wed, 24 Apr 2024 15:16:56 GMT
• Title: NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images
• Authors: Jingrui Yu, Dipankar Nandi, Roman Seidel, Gangolf Hirtz,
• Abstract summary: Human pose estimation (HPE) in the top-view using fisheye cameras presents a promising and innovative application domain. We leverage the capabilities of Neural Radiance Fields (NeRF) technique to establish a comprehensive pipeline for generating human pose datasets.
• Score: 1.86413150130483
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Human pose estimation (HPE) in the top-view using fisheye cameras presents a promising and innovative application domain. However, the availability of datasets capturing this viewpoint is extremely limited, especially those with high-quality 2D and 3D keypoint annotations. Addressing this gap, we leverage the capabilities of Neural Radiance Fields (NeRF) technique to establish a comprehensive pipeline for generating human pose datasets from existing 2D and 3D datasets, specifically tailored for the top-view fisheye perspective. Through this pipeline, we create a novel dataset NToP570K (NeRF-powered Top-view human Pose dataset for fisheye cameras with over 570 thousand images), and conduct an extensive evaluation of its efficacy in enhancing neural networks for 2D and 3D top-view human pose estimation. A pretrained ViTPose-B model achieves an improvement in AP of 33.3 % on our validation set for 2D HPE after finetuning on our training set. A similarly finetuned HybrIK-Transformer model gains 53.7 mm reduction in PA-MPJPE for 3D HPE on the validation set.

Related papers

• Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images [8.719294151596705]
  We evaluate the impact of pinhole, equidistant and double sphere camera models, as well as cylindrical projection methods, on 3D human pose estimation accuracy.<n>We find that in close-up scenarios, pinhole projection is inadequate, and the optimal projection method varies with the FOV covered by the human pose.<n>We propose a for selecting the appropriate projection model based on the detection bounding box to enhance prediction quality.
  arXiv  Detail & Related papers  (2025-06-24T16:05:36Z)
• Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision [0.3387808070669509]
  Egocentric human body estimation allows for the inference of user body pose and shape from a wearable camera's first-person perspective. We introduce Fish2Mesh, a fisheye-aware transformer-based model designed for 3D egocentric human mesh recovery. Our experiments demonstrate that Fish2Mesh outperforms previous state-of-the-art 3D HMR models.
  arXiv  Detail & Related papers  (2025-03-08T06:34:49Z)
• L3D-Pose: Lifting Pose for 3D Avatars from a Single Camera in the Wild [15.174438063000453]
  3D pose estimation provides a more comprehensive solution by incorporating depth, yet creating 3D pose datasets for animals is challenging due to their dynamic and unpredictable behaviours in natural settings. We propose a framework with systematically synthesized datasets for lifting poses from 2D to 3D and then utilize this to re-target motion from wild settings onto arbitrary avatars.
  arXiv  Detail & Related papers  (2025-01-02T10:04:12Z)
• CameraHMR: Aligning People with Perspective [54.05758012879385]
  We address the challenge of accurate 3D human pose and shape estimation from monocular images. Existing training datasets containing real images with pseudo ground truth (pGT) use SMPLify to fit SMPL to sparse 2D joint locations. We make two contributions that improve pGT accuracy.
  arXiv  Detail & Related papers  (2024-11-12T19:12:12Z)
• FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Camera [8.502741852406904]
  We present FisheyeDepth, a self-supervised depth estimation model tailored for fisheye cameras. We incorporate a fisheye camera model into the projection and reprojection stages during training to handle image distortions. We also incorporate real-scale pose information into the geometric projection between consecutive frames, replacing the poses estimated by the conventional pose network.
  arXiv  Detail & Related papers  (2024-09-23T14:31:42Z)
• Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes [65.22070581594426]
  "Implicit-Zoo" is a large-scale dataset requiring thousands of GPU training days to facilitate research and development in this field. We showcase two immediate benefits as it enables to: (1) learn token locations for transformer models; (2) directly regress 3D cameras poses of 2D images with respect to NeRF models. This in turn leads to an improved performance in all three task of image classification, semantic segmentation, and 3D pose regression, thereby unlocking new avenues for research.
  arXiv  Detail & Related papers  (2024-06-25T10:20:44Z)
• Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement [65.08165593201437]
  We explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion. This task presents significant challenges due to the lack of high-quality datasets, fisheye camera distortion, and human body self-occlusion. We propose a novel approach that leverages FisheyeViT to extract fisheye image features, which are converted into pixel-aligned 3D heatmap representations for 3D human body pose prediction.
  arXiv  Detail & Related papers  (2023-11-28T07:13:47Z)
• Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistency [0.493599216374976]
  We propose a novel loss function, multiview consistency, to enable adding additional training data with only 2D supervision. Our experiments demonstrate that two views offset by 90 degrees are enough to obtain good performance, with only marginal improvements by adding more views. This research introduces new possibilities for domain adaptation in 3D pose estimation, providing a practical and cost-effective solution to customize models for specific applications.
  arXiv  Detail & Related papers  (2023-11-21T08:21:55Z)
• CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations [25.05308239278207]
  We present CameraPose, a weakly-supervised framework for 3D human pose estimation from a single image. By adding a camera parameter branch, any in-the-wild 2D annotations can be fed into our pipeline to boost the training diversity. We also introduce a refinement network module with confidence-guided loss to further improve the quality of noisy 2D keypoints extracted by 2D pose estimators.
  arXiv  Detail & Related papers  (2023-01-08T05:07:41Z)
• UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture [70.59984501516084]
  UnrealEgo is a new large-scale naturalistic dataset for egocentric 3D human pose estimation. It is based on an advanced concept of eyeglasses equipped with two fisheye cameras that can be used in unconstrained environments. We propose a new benchmark method with a simple but effective idea of devising a 2D keypoint estimation module for stereo inputs to improve 3D human pose estimation.
  arXiv  Detail & Related papers  (2022-08-02T17:59:54Z)
• AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation [24.009674750548303]
  Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. We propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset. Our method outperforms previous work in cross-dataset evaluations by 14% and previous semi-supervised learning methods that use partial 3D annotations by 16%.
  arXiv  Detail & Related papers  (2021-12-22T00:27:52Z)
• Towards Generalization of 3D Human Pose Estimation In The Wild [73.19542580408971]
  3DBodyTex.Pose is a dataset that addresses the task of 3D human pose estimation in-the-wild. 3DBodyTex.Pose offers high quality and rich data containing 405 different real subjects in various clothing and poses, and 81k image samples with ground-truth 2D and 3D pose annotations.
  arXiv  Detail & Related papers  (2020-04-21T13:31:58Z)
• Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation [107.07047303858664]
  Large-scale human datasets with 3D ground-truth annotations are difficult to obtain in the wild. We address this problem by augmenting existing 2D datasets with high-quality 3D pose fits. The resulting annotations are sufficient to train from scratch 3D pose regressor networks that outperform the current state-of-the-art on in-the-wild benchmarks.
  arXiv  Detail & Related papers  (2020-04-07T20:21:18Z)

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.