GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    MyStyle : A Personalized Generative Prior
    Association for Computing Machinery (ACM) ; 2022
    In:  ACM Transactions on Graphics Vol. 41, No. 6 ( 2022-12), p. 1-10
    Details
    In: ACM Transactions on Graphics, Association for Computing Machinery (ACM), Vol. 41, No. 6 ( 2022-12), p. 1-10
    Abstract: We introduce MyStyle, a personalized deep generative prior trained with a few shots of an individual. MyStyle allows to reconstruct, enhance and edit images of a specific person, such that the output is faithful to the person's key facial characteristics. Given a small reference set of portrait images of a person (~ 100), we tune the weights of a pretrained StyleGAN face generator to form a local, low-dimensional, personalized manifold in the latent space. We show that this manifold constitutes a personalized region that spans latent codes associated with diverse portrait images of the individual. Moreover, we demonstrate that we obtain a personalized generative prior, and propose a unified approach to apply it to various ill-posed image enhancement problems, such as inpainting and super-resolution, as well as semantic editing. Using the personalized generative prior we obtain outputs that exhibit high-fidelity to the input images and are also faithful to the key facial characteristics of the individual in the reference set. We demonstrate our method with fair-use images of numerous widely recognizable individuals for whom we have the prior knowledge for a qualitative evaluation of the expected outcome. We evaluate our approach against few-shots baselines and show that our personalized prior, quantitatively and qualitatively, outperforms state-of-the-art alternatives.
    Type of Medium: Online Resource
    ISSN: 0730-0301 , 1557-7368
    URL: Article
    DOI: 10.1145/3550454.3555436
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2022
    detail.hit.zdb_id: 2006336-2
    detail.hit.zdb_id: 625686-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    GANimator : neural motion synthesis from a single sequence
    Association for Computing Machinery (ACM) ; 2022
    In:  ACM Transactions on Graphics Vol. 41, No. 4 ( 2022-07), p. 1-12
    Details
    In: ACM Transactions on Graphics, Association for Computing Machinery (ACM), Vol. 41, No. 4 ( 2022-07), p. 1-12
    Abstract: We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence. GANimator generates motions that resemble the core elements of the original motion, while simultaneously synthesizing novel and diverse movements. Existing data-driven techniques for motion synthesis require a large motion dataset which contains the desired and specific skeletal structure. By contrast, GANimator only requires training on a single motion sequence, enabling novel motion synthesis for a variety of skeletal structures e.g. , bipeds, quadropeds, hexapeds, and more. Our framework contains a series of generative and adversarial neural networks, each responsible for generating motions in a specific frame rate. The framework progressively learns to synthesize motion from random noise, enabling hierarchical control over the generated motion content across varying levels of detail. We show a number of applications, including crowd simulation, key-frame editing, style transfer, and interactive control, which all learn from a single input sequence. Code and data for this paper are at https://peizhuoli.github.io/ganimator.
    Type of Medium: Online Resource
    ISSN: 0730-0301 , 1557-7368
    URL: Article
    DOI: 10.1145/3528223.3530157
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2022
    detail.hit.zdb_id: 2006336-2
    detail.hit.zdb_id: 625686-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Learning skeletal articulations with neural blend shapes
    Association for Computing Machinery (ACM) ; 2021
    In:  ACM Transactions on Graphics Vol. 40, No. 4 ( 2021-08), p. 1-15
    Details
    In: ACM Transactions on Graphics, Association for Computing Machinery (ACM), Vol. 40, No. 4 ( 2021-08), p. 1-15
    Type of Medium: Online Resource
    ISSN: 0730-0301 , 1557-7368
    URL: Article
    DOI: 10.1145/3476576.3476702
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2021
    detail.hit.zdb_id: 2006336-2
    detail.hit.zdb_id: 625686-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    Learning character-agnostic motion for motion retargeting in 2D
    Association for Computing Machinery (ACM) ; 2019
    In:  ACM Transactions on Graphics Vol. 38, No. 4 ( 2019-08-31), p. 1-14
    Details
    In: ACM Transactions on Graphics, Association for Computing Machinery (ACM), Vol. 38, No. 4 ( 2019-08-31), p. 1-14
    Abstract: Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to another. While humans move in three dimensions, the vast majority of human motions are captured using video, requiring 2D-to-3D pose and camera recovery, before existing retargeting approaches may be applied. In this paper, we present a new method for retargeting video-captured motion between different human performers, without the need to explicitly reconstruct 3D poses and/or camera parameters. In order to achieve our goal, we learn to extract, directly from a video, a high-level latent motion representation, which is invariant to the skeleton geometry and the camera view. Our key idea is to train a deep neural network to decompose temporal sequences of 2D poses into three components: motion, skeleton, and camera view-angle. Having extracted such a representation, we are able to re-combine motion with novel skeletons and camera views, and decode a retargeted temporal sequence, which we compare to a ground truth from a synthetic dataset. We demonstrate that our framework can be used to robustly extract human motion from videos, bypassing 3D reconstruction, and outperforming existing retargeting methods, when applied to videos in-the-wild. It also enables additional applications, such as performance cloning, video-driven cartoons, and motion retrieval.
    Type of Medium: Online Resource
    ISSN: 0730-0301 , 1557-7368
    URL: Article
    DOI: 10.1145/3306346.3322999
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2019
    detail.hit.zdb_id: 2006336-2
    detail.hit.zdb_id: 625686-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 5
    Online Resource
    Online Resource
    Neural best-buddies : sparse cross-domain correspondence
    Association for Computing Machinery (ACM) ; 2018
    In:  ACM Transactions on Graphics Vol. 37, No. 4 ( 2018-08-31), p. 1-14
    Details
    In: ACM Transactions on Graphics, Association for Computing Machinery (ACM), Vol. 37, No. 4 ( 2018-08-31), p. 1-14
    Abstract: Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications. This paper presents a novel method for sparse cross-domain correspondence. Our method is designed for pairs of images where the main objects of interest may belong to different semantic categories and differ drastically in shape and appearance, yet still contain semantically related or geometrically similar parts. Our approach operates on hierarchies of deep features, extracted from the input images by a pre-trained CNN. Specifically, starting from the coarsest layer in both hierarchies, we search for Neural Best Buddies (NBB): pairs of neurons that are mutual nearest neighbors. The key idea is then to percolate NBBs through the hierarchy, while narrowing down the search regions at each level and retaining only NBBs with significant activations. Furthermore, in order to overcome differences in appearance, each pair of search regions is transformed into a common appearance. We evaluate our method via a user study, in addition to comparisons with alternative correspondence approaches. The usefulness of our method is demonstrated using a variety of graphics applications, including cross-domain image alignment, creation of hybrid images, automatic image morphing, and more.
    Type of Medium: Online Resource
    ISSN: 0730-0301 , 1557-7368
    URL: Article
    DOI: 10.1145/3197517.3201332
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2018
    detail.hit.zdb_id: 2006336-2
    detail.hit.zdb_id: 625686-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 6
    Online Resource
    Online Resource
    Learning skeletal articulations with neural blend shapes
    Association for Computing Machinery (ACM) ; 2021
    In:  ACM Transactions on Graphics Vol. 40, No. 4 ( 2021-08-31), p. 1-15
    Details
    In: ACM Transactions on Graphics, Association for Computing Machinery (ACM), Vol. 40, No. 4 ( 2021-08-31), p. 1-15
    Abstract: Animating a newly designed character using motion capture (mocap) data is a long standing problem in computer animation. A key consideration is the skeletal structure that should correspond to the available mocap data, and the shape deformation in the joint regions, which often requires a tailored, pose-specific refinement. In this work, we develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure which produces high quality pose dependent deformations. Our framework learns to rig and skin characters with the same articulation structure ( e.g. , bipeds or quadrupeds), and builds the desired skeleton hierarchy into the network architecture. Furthermore , we propose neural blend shapes - a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning. Our system estimates neural blend shapes for input meshes with arbitrary connectivity, as well as weighting coefficients which are conditioned on the input joint rotations. Unlike recent deep learning techniques which supervise the network with ground-truth rigging and skinning parameters, our approach does not assume that the training data has a specific underlying deformation model. Instead, during training, the network observes deformed shapes and learns to infer the corresponding rig, skin and blend shapes using indirect supervision. During inference, we demonstrate that our network generalizes to unseen characters with arbitrary mesh connectivity, including unrigged characters built by 3D artists. Conforming to standard skeletal animation models enables direct plug-and-play in standard animation software, as well as game engines.
    Type of Medium: Online Resource
    ISSN: 0730-0301 , 1557-7368
    URL: Article
    DOI: 10.1145/3450626.3459852
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2021
    detail.hit.zdb_id: 2006336-2
    detail.hit.zdb_id: 625686-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 7
    Online Resource
    Online Resource
    Skeleton-aware networks for deep motion retargeting
    Association for Computing Machinery (ACM) ; 2020
    In:  ACM Transactions on Graphics Vol. 39, No. 4 ( 2020-08-31)
    Details
    In: ACM Transactions on Graphics, Association for Computing Machinery (ACM), Vol. 39, No. 4 ( 2020-08-31)
    Abstract: We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, yet corresponding to homeomorphic graphs. Importantly, our approach learns how to retarget without requiring any explicit pairing between the motions in the training set. We leverage the fact that different homeomorphic skeletons may be reduced to a common primal skeleton by a sequence of edge merging operations, which we refer to as skeletal pooling. Thus, our main technical contribution is the introduction of novel differentiable convolution, pooling, and unpooling operators. These operators are skeleton-aware , meaning that they explicitly account for the skeleton's hierarchical structure and joint adjacency, and together they serve to transform the original motion into a collection of deep temporal features associated with the joints of the primal skeleton. In other words, our operators form the building blocks of a new deep motion processing framework that embeds the motion into a common latent space, shared by a collection of homeomorphic skeletons. Thus, retargeting can be achieved simply by encoding to, and decoding from this latent space. Our experiments show the effectiveness of our framework for motion retargeting, as well as motion processing in general, compared to existing approaches. Our approach is also quantitatively evaluated on a synthetic dataset that contains pairs of motions applied to different skeletons. To the best of our knowledge, our method is the first to perform retargeting between skeletons with differently sampled kinematic chains, without any paired examples.
    Type of Medium: Online Resource
    ISSN: 0730-0301 , 1557-7368
    URL: Article
    DOI: 10.1145/3386569.3392462
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2020
    detail.hit.zdb_id: 2006336-2
    detail.hit.zdb_id: 625686-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 8
    Online Resource
    Online Resource
    supp1-3163676.mp4
    Institute of Electrical and Electronics Engineers (IEEE) ; 2023
    In:  IEEE Transactions on Visualization and Computer Graphics Vol. 29, No. 8 ( 2023-8-1), p. 3519-3534
    Details
    In: IEEE Transactions on Visualization and Computer Graphics, Institute of Electrical and Electronics Engineers (IEEE), Vol. 29, No. 8 ( 2023-8-1), p. 3519-3534
    Type of Medium: Online Resource
    ISSN: 1077-2626 , 1941-0506 , 2160-9306
    URL: Article
    URL: Article
    DOI: 10.1109/TVCG.2022.3163676
    DOI: 10.1109/TVCG.2022.3163676/mm1
    RVK:
    SQ 1100
    Language: Unknown
    Publisher: Institute of Electrical and Electronics Engineers (IEEE)
    Publication Date: 2023
    detail.hit.zdb_id: 2027333-2
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 9
    Online Resource
    Online Resource
    Sub-Nyquist SAR via Fourier Domain Range-Doppler Processing
    Institute of Electrical and Electronics Engineers (IEEE) ; 2017
    In:  IEEE Transactions on Geoscience and Remote Sensing Vol. 55, No. 11 ( 2017-11), p. 6228-6244
    Details
    In: IEEE Transactions on Geoscience and Remote Sensing, Institute of Electrical and Electronics Engineers (IEEE), Vol. 55, No. 11 ( 2017-11), p. 6228-6244
    Type of Medium: Online Resource
    ISSN: 0196-2892 , 1558-0644
    URL: Article
    DOI: 10.1109/TGRS.2017.2723620
    Language: Unknown
    Publisher: Institute of Electrical and Electronics Engineers (IEEE)
    Publication Date: 2017
    detail.hit.zdb_id: 2027520-1
    SSG: 16,13
    SSG: 13
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 10
    Online Resource
    Online Resource
    MotioNet : 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency
    Association for Computing Machinery (ACM) ; 2021
    In:  ACM Transactions on Graphics Vol. 40, No. 1 ( 2021-02-28), p. 1-15
    Details
    In: ACM Transactions on Graphics, Association for Computing Machinery (ACM), Vol. 40, No. 1 ( 2021-02-28), p. 1-15
    Abstract: We introduce MotioNet , a deep neural network that directly reconstructs the motion of a 3D human skeleton from a monocular video. While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with temporally coherent joint rotations, our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used motion representation. At the crux of our approach lies a deep neural network with embedded kinematic priors, which decomposes sequences of 2D joint positions into two separate attributes: a single, symmetric skeleton encoded by bone lengths, and a sequence of 3D joint rotations associated with global root positions and foot contact labels. These attributes are fed into an integrated forward kinematics (FK) layer that outputs 3D positions, which are compared to a ground truth. In addition, an adversarial loss is applied to the velocities of the recovered rotations to ensure that they lie on the manifold of natural joint rotations. The key advantage of our approach is that it learns to infer natural joint rotations directly from the training data rather than assuming an underlying model, or inferring them from joint positions using a data-agnostic IK solver. We show that enforcing a single consistent skeleton along with temporally coherent joint rotations constrains the solution space, leading to a more robust handling of self-occlusions and depth ambiguities.
    Type of Medium: Online Resource
    ISSN: 0730-0301 , 1557-7368
    URL: Article
    DOI: 10.1145/3407659
    Language: English
    Publisher: Association for Computing Machinery (ACM)
    Publication Date: 2021
    detail.hit.zdb_id: 2006336-2
    detail.hit.zdb_id: 625686-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...