Literature Review Survey Articles

Article Deep Learning-Based Human Pose Estimation: A Survey:

• Survey of deep learning methods for human pose estimation.

Recovering 3D Human Mesh from Monocular Images: A Survey:

• Survey of human 3D mesh estimation.

Classic Mocap

• Article SMPL: A Skinned Multi-Person Linear Model:
  • Key paper for traditional methods.
• Article Embodied Hands: Modeling and Capturing Hands and Bodies Together:
  • Capturing hands and bodies together.
• Article SMPLify:
  • Estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image

Diffusion Based Motion Generation Models

• Article+Code MDM: Human Motion Diffusion Model:
  • Human motion generation
• Article Motion Diffuse:
  • Human motion generation
• Article HUMAN MOTION DIFFUSION MODEL:
  • Human motion generation

LLM Based Motion Generation Models

• Article+Code MotionGPT: Human Motion as a Foreign Language:
  • Human motion generation
• Article+Code MotionGPT: Finetuned LLMs are General-Purpose Motion Generators:
  • Human motion generation

General Articles

• Article+Video Results MPhysDiff: Physics-Guided Human Motion Diffusion Model:
  • Physically-plausible motions using a physics-based motion projection
• Article Action-GPT:
  • a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models
• Repo Action-GPT:
  • a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models
• Website Action-GPT:
  • a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models
• Article TEACH
  • TEACH: Temporal Action Compositions for 3D Humans Given a series of natural language descriptions, our task is to generate 3D human motions that correspond semantically to the text, and follow the temporal order of the instructions.
• Repo TEACH
  • TEACH: Temporal Action Compositions for 3D Humans Given a series of natural language descriptions, our task is to generate 3D human motions that correspond semantically to the text, and follow the temporal order of the instructions.
• Website TEACH
  • TEACH: Temporal Action Compositions for 3D Humans Given a series of natural language descriptions, our task is to generate 3D human motions that correspond semantically to the text, and follow the temporal order of the instructions.
• Article MotionCLIP:
  • MotionCLIP, a 3D human motion auto-encoder featuring a latent embedding that is disentangled, well behaved, and supports highly se-mantic textual descriptions
• Repo MotionCLIP:
  • MotionCLIP, a 3D human motion auto-encoder featuring a latent embedding that is disentangled, well behaved, and supports highly se-mantic textual descriptions
• Website MotionCLIP:
  • MotionCLIP, a 3D human motion auto-encoder featuring a latent embedding that is disentangled, well behaved, and supports highly se-mantic textual descriptions