A single transformer model jointly predicts depth and normalized canonical coordinates to deliver state-of-the-art 4D facial geometry and tracking with 3x lower correspondence error and 16% better depth accuracy.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Face Anything: 4D Face Reconstruction from Any Image Sequence
A single transformer model jointly predicts depth and normalized canonical coordinates to deliver state-of-the-art 4D facial geometry and tracking with 3x lower correspondence error and 16% better depth accuracy.
-
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.