Reproduce “ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting” 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
Houqiang Zhong, Tianchi Zhu, Qiang Hu, Xiaoyun Zhang, Li Song, Wenjun Zhang
ACD-GS guides 3D Gaussian Splatting densification using curvature in depth maps rendered from its current Gaussians, suppressing cloning and promoting splitting near depth boundaries while applying multi-view photometric gating. On Deep Blending, it uses 0.642 million Gaussians and 151.90 MB, versus 1.550 million and 367.30 MB for 3DGS, with higher PSNR and SSIM but worse LPIPS than 3DGS.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.