Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048450092> ?p ?o ?g. }
- W3048450092 abstract "Robotic grasping of house-hold objects has made remarkable progress in recent years. Yet, human grasps are still difficult to synthesize realistically. There are several key reasons: (1) the human hand has many degrees of freedom (more than robotic manipulators); (2) the synthesized hand should conform to the surface of the object; and (3) it should interact with the object in a semantically and physically plausible manner. To make progress in this direction, we draw inspiration from the recent progress on learning-based implicit representations for 3D object reconstruction. Specifically, we propose an expressive representation for human grasp modelling that is efficient and easy to integrate with deep neural networks. Our insight is that every point in a three-dimensional space can be characterized by the signed distances to the surface of the hand and the object, respectively. Consequently, the hand, the object, and the contact area can be represented by implicit surfaces in a common space, in which the proximity between the hand and the object can be modelled explicitly. We name this 3D to 2D mapping as Grasping Field, parameterize it with a deep neural network, and learn it from data. We demonstrate that the proposed grasping field is an effective and expressive representation for human grasp generation. Specifically, our generative model is able to synthesize high-quality human grasps, given only on a 3D object point cloud. The extensive experiments demonstrate that our generative model compares favorably with a strong baseline and approaches the level of natural human grasps. Our method improves the physical plausibility of the hand-object contact reconstruction and achieves comparable performance for 3D hand reconstruction compared to state-of-the-art methods." @default.
- W3048450092 created "2020-08-18" @default.
- W3048450092 creator A5033672325 @default.
- W3048450092 creator A5035023688 @default.
- W3048450092 creator A5056265728 @default.
- W3048450092 creator A5062785485 @default.
- W3048450092 creator A5065396778 @default.
- W3048450092 creator A5086664284 @default.
- W3048450092 date "2020-08-10" @default.
- W3048450092 modified "2023-09-23" @default.
- W3048450092 title "Grasping Field: Learning Implicit Representations for Human Grasps" @default.
- W3048450092 cites W1500711968 @default.
- W3048450092 cites W1510186039 @default.
- W3048450092 cites W1551609627 @default.
- W3048450092 cites W1892339738 @default.
- W3048450092 cites W1906662973 @default.
- W3048450092 cites W1913984289 @default.
- W3048450092 cites W1940481278 @default.
- W3048450092 cites W1959608418 @default.
- W3048450092 cites W1966073502 @default.
- W3048450092 cites W1968976745 @default.
- W3048450092 cites W2087379739 @default.
- W3048450092 cites W2088706594 @default.
- W3048450092 cites W2102393714 @default.
- W3048450092 cites W2117539524 @default.
- W3048450092 cites W2122115534 @default.
- W3048450092 cites W2131213558 @default.
- W3048450092 cites W2136390383 @default.
- W3048450092 cites W2139760425 @default.
- W3048450092 cites W2149729559 @default.
- W3048450092 cites W2153169563 @default.
- W3048450092 cites W2169482286 @default.
- W3048450092 cites W2190691619 @default.
- W3048450092 cites W2194775991 @default.
- W3048450092 cites W2201912979 @default.
- W3048450092 cites W2210697964 @default.
- W3048450092 cites W2211722331 @default.
- W3048450092 cites W2214145768 @default.
- W3048450092 cites W2227547437 @default.
- W3048450092 cites W2229412420 @default.
- W3048450092 cites W2282481780 @default.
- W3048450092 cites W2340988230 @default.
- W3048450092 cites W2516753435 @default.
- W3048450092 cites W2520346623 @default.
- W3048450092 cites W2527587652 @default.
- W3048450092 cites W2543872873 @default.
- W3048450092 cites W2560609797 @default.
- W3048450092 cites W2560722161 @default.
- W3048450092 cites W2566261308 @default.
- W3048450092 cites W2605973302 @default.
- W3048450092 cites W2606627193 @default.
- W3048450092 cites W2754340109 @default.
- W3048450092 cites W2768683308 @default.
- W3048450092 cites W2784142237 @default.
- W3048450092 cites W2798581336 @default.
- W3048450092 cites W2886134824 @default.
- W3048450092 cites W2889146482 @default.
- W3048450092 cites W2894714230 @default.
- W3048450092 cites W2897577167 @default.
- W3048450092 cites W2897765997 @default.
- W3048450092 cites W2910474428 @default.
- W3048450092 cites W2914390273 @default.
- W3048450092 cites W2956872328 @default.
- W3048450092 cites W2962778872 @default.
- W3048450092 cites W2962811204 @default.
- W3048450092 cites W2962849139 @default.
- W3048450092 cites W2962885944 @default.
- W3048450092 cites W2962926199 @default.
- W3048450092 cites W2963207848 @default.
- W3048450092 cites W2963433432 @default.
- W3048450092 cites W2963488642 @default.
- W3048450092 cites W2963527086 @default.
- W3048450092 cites W2963601560 @default.
- W3048450092 cites W2963627347 @default.
- W3048450092 cites W2963926543 @default.
- W3048450092 cites W2964027736 @default.
- W3048450092 cites W2964121744 @default.
- W3048450092 cites W2964249569 @default.
- W3048450092 cites W2968722025 @default.
- W3048450092 cites W2973857456 @default.
- W3048450092 cites W2980216391 @default.
- W3048450092 cites W2981657250 @default.
- W3048450092 cites W2982275673 @default.
- W3048450092 cites W2984210651 @default.
- W3048450092 cites W2984612350 @default.
- W3048450092 cites W2985034589 @default.
- W3048450092 cites W3015636086 @default.
- W3048450092 cites W3021322563 @default.
- W3048450092 cites W3034470433 @default.
- W3048450092 cites W3034479523 @default.
- W3048450092 cites W3034681090 @default.
- W3048450092 cites W3034891989 @default.
- W3048450092 cites W3035163517 @default.
- W3048450092 cites W3035467087 @default.
- W3048450092 cites W3035591705 @default.
- W3048450092 cites W3035724791 @default.
- W3048450092 cites W3099926824 @default.
- W3048450092 cites W3109929115 @default.
- W3048450092 cites W3112422759 @default.
- W3048450092 cites W48480781 @default.