CLONE estimates surface normals from images via a differentiable 3D Gaussian splatting loop, using photometric loss instead of normal labels.
Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CLONE: Continuous Latent Optimization for Normal Estimation via 3D Gaussian Splatting
CLONE estimates surface normals from images via a differentiable 3D Gaussian splatting loop, using photometric loss instead of normal labels.