3D Hand Pose Estimation in Everyday Egocentric Images

• URL: http://arxiv.org/abs/2312.06583v2
• Date: Mon, 23 Sep 2024 14:32:08 GMT
• Title: 3D Hand Pose Estimation in Everyday Egocentric Images
• Authors: Aditya Prakash, Ruisen Tu, Matthew Chang, Saurabh Gupta,
• Abstract summary: We focus on challenges arising from perspective distortion and lack of 3D annotations in the wild. We present WildHands, a system for 3D hand pose estimation in everyday egocentric images.
• Score: 12.964086079352262
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D hand pose estimation in everyday egocentric images is challenging for several reasons: poor visual signal (occlusion from the object of interaction, low resolution & motion blur), large perspective distortion (hands are close to the camera), and lack of 3D annotations outside of controlled settings. While existing methods often use hand crops as input to focus on fine-grained visual information to deal with poor visual signal, the challenges arising from perspective distortion and lack of 3D annotations in the wild have not been systematically studied. We focus on this gap and explore the impact of different practices, i.e. crops as input, incorporating camera information, auxiliary supervision, scaling up datasets. We provide several insights that are applicable to both convolutional and transformer models leading to better performance. Based on our findings, we also present WildHands, a system for 3D hand pose estimation in everyday egocentric images. Zero-shot evaluation on 4 diverse datasets (H2O, AssemblyHands, Epic-Kitchens, Ego-Exo4D) demonstrate the effectiveness of our approach across 2D and 3D metrics, where we beat past methods by 7.4% - 66%. In system level comparisons, WildHands achieves the best 3D hand pose on ARCTIC egocentric split, outperforms FrankMocap across all metrics and HaMeR on 3 out of 6 metrics while being 10x smaller and trained on 5x less data.

Related papers

• Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation [41.96019347138128]
  We propose learning direction-aware hybrid features (DaHyF) that fuse implicit image features and explicit 2D joint coordinate features. Our method directly predicts 3D hand poses with DaHyF representation and reduces jittering during motion capture using prediction confidence based on contrastive learning.
  arXiv  Detail & Related papers  (2025-04-02T02:06:23Z)
• Any6D: Model-free 6D Pose Estimation of Novel Objects [76.30057578269668]
  We introduce Any6D, a model-free framework for 6D object pose estimation. It requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. We evaluate our method on five challenging datasets.
  arXiv  Detail & Related papers  (2025-03-24T13:46:21Z)
• AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation [26.261767086366866]
  We present AssemblyHands, a large-scale benchmark dataset with accurate 3D hand pose annotations. AssemblyHands provides 3.0M annotated images, including 490K egocentric images. Our study shows that having higher-quality hand poses directly improves the ability to recognize actions.
  arXiv  Detail & Related papers  (2023-04-24T17:52:57Z)
• MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision [72.5863451123577]
  We show how to train a neural model that can perform accurate 3D pose and camera estimation. Our method outperforms both classical bundle adjustment and weakly-supervised monocular 3D baselines.
  arXiv  Detail & Related papers  (2021-08-10T18:39:56Z)
• CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild [31.334715988245748]
  We propose a self-supervised approach that learns a single image 3D pose estimator from unlabeled multi-view data. In contrast to most existing methods, we do not require calibrated cameras and can therefore learn from moving cameras. Key to the success are new, unbiased reconstruction objectives that mix information across views and training samples.
  arXiv  Detail & Related papers  (2020-11-30T10:42:27Z)
• SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera [97.0162841635425]
  We present a solution to egocentric 3D body pose estimation from monocular images captured from downward looking fish-eye cameras installed on the rim of a head mounted VR device. This unusual viewpoint leads to images with unique visual appearance, with severe self-occlusions and perspective distortions. We propose an encoder-decoder architecture with a novel multi-branch decoder designed to account for the varying uncertainty in 2D predictions.
  arXiv  Detail & Related papers  (2020-11-02T16:18:06Z)
• Exploring Severe Occlusion: Multi-Person 3D Pose Estimation with Gated Convolution [34.301501457959056]
  We propose a temporal regression network with a gated convolution module to transform 2D joints to 3D. A simple yet effective localization approach is also conducted to transform the normalized pose to the global trajectory. Our proposed method outperforms most state-of-the-art 2D-to-3D pose estimation methods.
  arXiv  Detail & Related papers  (2020-10-31T04:35:24Z)
• Synthetic Training for Monocular Human Mesh Recovery [100.38109761268639]
  This paper aims to estimate 3D mesh of multiple body parts with large-scale differences from a single RGB image. The main challenge is lacking training data that have complete 3D annotations of all body parts in 2D images. We propose a depth-to-scale (D2S) projection to incorporate the depth difference into the projection function to derive per-joint scale variants.
  arXiv  Detail & Related papers  (2020-10-27T03:31:35Z)
• MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis [81.40640219844197]
  Estimating the 3D hand pose from a monocular RGB image is important but challenging. A solution is training on large-scale RGB hand images with accurate 3D hand keypoint annotations. We have developed a learning-based approach to synthesize realistic, diverse, and 3D pose-preserving hand images.
  arXiv  Detail & Related papers  (2020-10-02T18:27:34Z)
• Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis [72.34794624243281]
  We propose a self-supervised learning framework to disentangle variations from unlabeled video frames. Our differentiable formalization, bridging the representation gap between the 3D pose and spatial part maps, allows us to operate on videos with diverse camera movements.
  arXiv  Detail & Related papers  (2020-04-09T07:55:01Z)
• Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision [0.0]
  We introduce a network that can be trained with additional RGB-D images in a weakly supervised fashion. Our algorithm is a monocular, multi-person, absolute pose estimator. We evaluate the algorithm on several benchmarks, showing a consistent improvement in error rates.
  arXiv  Detail & Related papers  (2020-04-08T13:29:22Z)
• Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction [137.28465645405655]
  HANDS'19 is a challenge to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on poses absent from the training set.
  arXiv  Detail & Related papers  (2020-03-30T19:28:13Z)
• Silhouette-Net: 3D Hand Pose Estimation from Silhouettes [16.266199156878056]
  Existing approaches mainly consider different input modalities and settings, such as monocular RGB, multi-view RGB, depth, or point cloud. We present a new architecture that automatically learns a guidance from implicit depth perception and solves the ambiguity of hand pose through end-to-end training.
  arXiv  Detail & Related papers  (2019-12-28T10:29:42Z)

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.