Reproduce “3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning” 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
Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, Laszlo A. Jeni, Fernando De la Torre
RSC-Net estimates 3D human pose and shape from a single image across the tested resolutions. It shares most of its network across resolutions and uses higher-resolution predictions to guide lower-resolution outputs, alongside contrastive feature learning across views of the same image. On 3DPW at 32 × 32, it reports MPJPE of 117.12 versus SPIN’s 137.61; this comparison is limited to the tested setup.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.