Gaussian Wrapping introduces oriented normals and a derived occupancy field to 3DGS, enabling high-fidelity watertight mesh extraction that sets new SOTA on DTU and Tanks and Temples while recovering thin structures.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
A transformer-based model jointly predicts depth and canonical facial coordinates to achieve unified, feed-forward 4D face reconstruction and dense tracking from image sequences.
citing papers explorer
-
From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians
Gaussian Wrapping introduces oriented normals and a derived occupancy field to 3DGS, enabling high-fidelity watertight mesh extraction that sets new SOTA on DTU and Tanks and Temples while recovering thin structures.
-
Face Anything: 4D Face Reconstruction from Any Image Sequence
A transformer-based model jointly predicts depth and canonical facial coordinates to achieve unified, feed-forward 4D face reconstruction and dense tracking from image sequences.