SOURCE-LINKED INTELLIGENCE

NormLift: From Lifted Features To Semantic Reliability In 3D Gaussian Splatting

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Training-free weighted aggregation is widely used to lift 2D semantic features onto 3D Gaussians for open-vocabulary scene understanding, yet its theoretical role remains insufficiently understood. Existing analyses typically justify this operation from the rendering side, treating Gaussian features as linearly composable Euclidean variables for reconstructing 2D feature maps. However, this view does not match downstream 3D usage, where each Gaussian is often queried independently in a cosine-based embedding space. We revisit feature lifting from the 3D side and formulate per-Gaussian assignme

Read original source ↗ Open in workspace

recordType

paper

region

Global