poetrywanderer / 3D-Reconstruction_paper_survey

3D Reconstruction Papers Survey

Personal repository to track my paper surveys. Based on Yagami360/MachineLearning-Papers_Survey.

Each paper summary is under Issues.

• Papers I intend to start soon are labeled TODO
• Process is labeled by percentage 30%, 50%, 80%, 100%

■ 3D Human Reconstruction

◎ Naked Human Reconstruction

• TODO

◎ Clothed Human Reconstruction

↳ non-parametric models (template-free)

• Voxel based
  • DeepHuman
• implicit function based
  • PiFu
  • PiFuHD

↳ parametric models (template based)

Research line

Based human body statistical models:

• SCAPE (2005)
• SMPL (2015)

Related papers:

• MGN:Multi-Garment Net: Learning to Dress 3D People from Images
• DeepFashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images
• TailorNet: TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style
• BCNet

↳ TODO papers

◎ 3D Human Dataset

◎ TODO

Cited paper on Google Scholar

■ Reference site

◎ Convenient sites

• PapersWithCode.com: check if a paper is implemented
• SemanticScholar.org: uses ML to cluster related papers, create custom paper feeds
• ConnectedPapers.com: visualize a graph of related papers

◎ Other reference sites

• Yagami360/MachineLearning-Papers_Survey
• andrewjong/Deep-Learning-Paper-Surveys