Reproduce “LiHi-GS: LiDAR-Supervised Gaussian Splatting for Highway Driving Scene 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
Pou-Chun Kung, Xianling Zhang, Katherine A. Skinner, Nikita Jaipuria
LiHi-GS reconstructs highway driving scenes from camera and LiDAR data for novel-view rendering and scenario editing. It renders supervision in camera-image and LiDAR range-image coordinates, with modeling for LiDAR visibility, uncertain depths, and camera–LiDAR actor-pose mismatch. On four short highway segments, it reports moving-object PSNR of 26.43 and LiDAR mean L1 error of 1.66, but not the best median error.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.