Reproduce “mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jiarui Yang, Songpengcheng Xia, Zengyuan Lai, Lan Sun, Qi Wu, Wenxian Yu, Ling Pei
mmDEAR reconstructs bodies from sparse mmWave radar sequences. It learns enhanced clouds using image-derived masks only during training, then combines enhanced and raw points to predict pose, shape, and translation. On mmBody, it reports 22.67 cm MPJPE and 17.25 cm MPVPE versus mmBaT’s 25.10 and 19.91 cm. MRI has joint-only ground truth; mmDEAR trails mmBaT on translation and joint-rotation error.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.