ContactPose: A Dataset of Grasps with Object Contact and Hand Pose

Brahmbhatt, Samarth; Tang, Chengcheng; Twigg, Christopher D.; Kemp, Charles C.; Hays, James

doi:10.1007/978-3-030-58601-0_22

Cited by 132 publications

(86 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As physical contact is fundamental to hand-object interaction, researchers have proposed methods to capture and modeling contact from diverse modalities [5,42], but these often interfere with natural movement. Concurrent to this work, [7] proposed a new dataset of hand-object contact paired with RGB-D images. Our work differs in that our focus is on learning an interaction representation, which is efficient and easy to interface with deep neural networks.…”

Section: Related Workmentioning

confidence: 99%

Grasping Field: Learning Implicit Representations for Human Grasps

Karunratanakul

Yang

Zhang

et al. 2020

2020 International Conference on 3D Vision (3DV)

168

122

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Grasping Field: Learning Implicit Representations for Human Grasps

Karunratanakul

Yang

Zhang

et al. 2020

2020 International Conference on 3D Vision (3DV)

168

122

View full text Add to dashboard Cite

show abstract

“…In terms of image synthesis, Ob-Man [18] leveraged virtual avatars that pose grasping hand in a simulator and rendered images through virtual cameras. ContactPose [1] synthesized images through real hand and background composition. In terms of pose synthesis, there are also two genres included in literature.…”

Section: Related Workmentioning

confidence: 99%

“…First, it is impractical to ask the subjects to systematically change their hand pose when interacting with object during recording. Second, different annotation approaches [1,8,13] may hinder the diversity unintentionally. For example, the multi-view-based approaches [1,13] require the subject to maintain a predefined and static grasping pose in a video sequence.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis

Li¹,

Yang²,

Zhan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Estimating the articulated 3D hand-object pose from a single RGB image is a highly ambiguous and challenging problem requiring large-scale datasets that contain diverse hand poses, object poses, and camera viewpoints. Most real-world datasets lack this diversity. In contrast, synthetic datasets can easily ensure vast diversity, but learning from them is inefficient and suffers from heavy training consumption. To address the above issues, we propose ArtiBoost, a lightweight online data enrichment method that boosts articulated hand-object pose estimation from the data perspective. ArtiBoost is employed along with a real-world source dataset. During training, ArtiBoost alternatively performs data exploration and synthesis. Art-iBoost can cover various hand-object poses and camera viewpoints based on a Compositional hand-object Configuration and Viewpoint space (CCV-space) and can adaptively enrich the current hard-discernable samples by a mining strategy. We apply ArtiBoost on a simple learning baseline network and demonstrate the performance boost on several hand-object benchmarks. As an illustrative example, with ArtiBoost, even a simple baseline network can outperform the previous start-of-the-art based on Transformer on the HO3D dataset. Our code is available at https://github.com/MVIG-SJTU/ArtiBoost.

show abstract

“…Hand-object interaction. There have been many studies into hand interaction with objects in various settings [5,7,9,12,17,18,23,24,29,31,42,59]. Recently, the community has begun exploring the task of generating plausible hand grasps given an object with notable studies including [12], [29], and [59].…”

Section: Related Workmentioning

confidence: 99%

A Skeleton-Driven Neural Occupancy Representation for Articulated Hands

Karunratanakul

Spurr

Fan

et al. 2021

2021 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

adrian.spurr,zicong.fan,otmar.hilliges,siyu.tang}@inf.ethz.ch https://korrawe.github.io/halo Figure 1. We introduce a novel neural implicit surface representation of human hands (HALO) that is fully driven by keypoint-based skeleton articulation. Taking 3D keypoints as input, a fully differentiable implicit occupancy representation produces high-fidelity reconstruction of the hand surface (top row). We show that HALO facilitates the conditional generation of articulated hands that grasp 3D objects in a realistic and physically plausible manner (bottom row).

show abstract

ContactPose: A Dataset of Grasps with Object Contact and Hand Pose

Cited by 132 publications

References 51 publications

Grasping Field: Learning Implicit Representations for Human Grasps

Grasping Field: Learning Implicit Representations for Human Grasps

ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis

A Skeleton-Driven Neural Occupancy Representation for Articulated Hands

Contact Info

Product

Resources

About