Reproduce “LighTROcc: Lightweight 4D Occupancy Forecasting via Instance-Centric 3D Gaussians” 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
Hwanhee Jung, SeungHyeon Kim, Inkyu Koo, Qixing Huang, Sang Ho Yoon, Sangpil Kim
LighTROcc forecasts general movable object occupancy by representing objects as instance-specific Gaussian mixtures and propagating them along predicted trajectories. Image attention and depth localize queries in 3D, while temporal query states provide memory. On supplemented nuScenes occupancy labels, it reports IoU_avg 16.19 and AP_avg 35.20 at 12.80 FPS; on original sparse labels, it leads aggregate metrics, but not every metric.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.