Self-supervised method for 3D human pose estimation with consistent shape and viewpoint factorization

Ma, Zhichao; Li, Kan; Li, Yang

doi:10.1007/s10489-022-03714-x

Cited by 4 publications

(1 citation statement)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [31] advanced this approach by proposing the Deep-NRSFM++ model, which accounted for more realistic situations, including perspective projection cameras and critical occlusion. Ma et al [32] built upon this approach by incorporating multi-view information and designing a simple yet effective loss function to ensure decomposition consistency. Subsequently, Zeng et al [33] proposed a new residual recurrent network and introduced the Minimal Singular Value Ratio (MSR) as a metric for measuring shape rigidity between two frames.…”

Section: Neural-network-based Solutions For Nrsfmmentioning

confidence: 99%

Temporal-Aware Neural Network for Dense Non-Rigid Structure from Motion

Wang,

Xu,

Huang

et al. 2023

Electronics

View full text Add to dashboard Cite

Modern neural networks addressing dense Non-Rigid Structure from Motion (NRSFM) dilemmas often grapple with intricate a priori constraints, deterring scalability, or overlook the imperative of consistent application of a priori knowledge throughout the entire input sequence. In this paper, an innovative neural network architecture is introduced. Initially, the complete 2D sequence image undergoes embedding into a low-dimensional space. Subsequently, multiple self-attention layers are employed to extract inter-frame features, with the objective of deriving a more continuous and temporally smooth low-dimensional structure closely resembling real data’s intrinsic structure. Moreover, it has been demonstrated by others that gradient descent during the training of multilayer linear networks yields minimum rank solutions, implicitly providing regularization that is equally applicable to this task. Benefiting from the excellence of the proposed network architecture, no additional a priori knowledge is mandated, barring the constraint of temporal smoothness. Extensive experimentation confirms the method’s exceptional performance in addressing dense NRSFM challenges, outperforming recent results across various dense benchmark datasets.

show abstract

Section: Neural-network-based Solutions For Nrsfmmentioning

confidence: 99%