PAME: Self-Supervised Masked Autoencoder for No-Reference Point Cloud Quality Assessment
Proposing a self-supervised pre-training framework using masked autoencoders (PAME) to enhance point cloud quality assessment without reference.
CrIBo: Self-Supervised Learning Method for Dense Visual Representation Learning
CrIBo introduces a novel method for self-supervised learning tailored to enhance dense visual representation learning.
LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
LeOCLR introduces a new approach to contrastive instance discrimination, improving representation learning by leveraging original images.
Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation
Diffusion-driven self-supervised network for multi-object shape reconstruction and categorical pose estimation.
FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning
FroSSL achieves faster convergence and competitive accuracies in self-supervised learning by minimizing covariance Frobenius norms.
Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning
Balancing stability and plasticity is crucial for effective continual self-supervised learning.
CrIBo: Self-Supervised Learning Method for Dense Visual Representation Learning
CrIBo introduces a novel method for self-supervised learning tailored to enhance dense visual representation learning.
DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos
Proposing a self-supervised method to jointly learn 3D motion and depth from monocular videos, benefiting both depth and 3D motion estimation.
© 2024 by Linnk AI