search

graphdeco-inria / hierarchical-3d-gaussians

Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"
Other
931 stars 87 forks source link

consolidation question #34

Open jianglh-WHU opened 2 months ago

jianglh-WHU commented 2 months ago

Thank you for your excellent work. I have a quick question. In the paper, you mentioned, "During the consolidation phase, if a primitive associated with—but outside—chunk 𝑖 is closer to another chunk 𝑗 ≠ 𝑖, it is deleted." How do you determine which chunk a primitive is closer to? I look forward to your response. Thanks again!

ameuleman commented 2 months ago

Hi, We use the Gaussian mean as the primitive's position and the centre of each chunk. We determine the closest chunk to a primitive by computing the distance between its mean and each chunk centre.