Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction

This paper presents an ensemble data assimilation method using the pseudo ensembles generated by denoising diffusion probabilistic model.

Denoising Diffusion Models (DDM) are emerging as the cutting-edge technology in the realm of deep generative modeling, challenging the dominance of Generative Adversarial Networks.

Based on the modeling method, we present FocusFlow, a framework consisting of 1) a mix loss function combined with a classic photometric loss function and our proposed Conditional Point Control Loss (CPCL) function for diverse point-wise supervision; 2) a conditioned controlling model which substitutes the conventional feature encoder by our proposed Condition Control Encoder (CCE).

Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs.

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.

LAMA utilizes a reinforcement learning framework combined with a motion matching algorithm. Reinforcement learning helps the model make appropriate decisions in various scenarios, while motion matching algorithms ensure that synthesized actions match real human actions. In addition, LAMA also utilizes the motion editing framework of manifold learning to cover various possible changes in interactions and operations.