Reproduce “VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis” 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
Angtian Wang, Peng Wang, Jian Sun, Adam Kortylewski, Alan Yuille
VoGE is a differentiable renderer that represents scenes as 3D Gaussian ellipsoids and blends their contributions using density along viewing rays and transmittance. It approximates density integration and provides gradients to occluded primitives. In NeMo pose estimation on the L3 Occluded PASCAL3D+ split, mean ACCπ/6 is 56.0% versus 46.8% with PyTorch3D, a result limited to this renderer-integration setup.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.