Reproduce “Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic 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
Decai Chen, Brianne Oberson, Ingo Feldmann, Oliver Schreer, Anna Hilsmann, Peter Eisert
AT-GS reconstructs calibrated multi-camera video as novel-view renderings and surface meshes over time. It initializes each frame’s Gaussian-surfel representation from the preceding frame, adapts surfels through gradient-guided densification, and uses curvature consistency to encourage temporal stability. On DNA-Rendering, it averages PSNR 35.44, SSIM 0.988, and LPIPS 0.024 across five scenes; geometry comparisons remain qualitative because ground truth is unavailable.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.