Search Results for author:
Found 9 papers, 9 papers with code
SPARF: Neural Radiance Fields from Sparse and Noisy Poses
Neural Radiance Field (NeRF) has recently emerged as a powerful representation to synthesize photorealistic novel views.
Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
Due to the scarcity of dense pixel-level semantic annotations for images recorded in adverse visual conditions, there has been a keen interest in unsupervised domain adaptation (UDA) for the semantic segmentation of such images.
Ranked #1 on
Semantic Segmentation
on Dark Zurich
Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching.
PDC-Net+: Enhanced Probabilistic Dense Correspondence Network
In order to apply dense methods to real-world applications, such as pose estimation, image manipulation, or 3D reconstruction, it is therefore crucial to estimate the confidence of the predicted matches.
Warp Consistency for Unsupervised Learning of Dense Correspondences
From our observations and empirical results, we design a general unsupervised objective employing two of the derived constraints.
Learning Accurate Dense Correspondences and When to Trust Them
Establishing dense correspondences between a pair of images is an important and general problem.
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
We propose GOCor, a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer.
Dense Pixel Correspondence Estimation
Feature Correlation
+2
GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences
Establishing dense correspondences between a pair of images is an important and general problem, covering geometric matching, optical flow and semantic correspondences.
GLAMpoints: Greedily Learned Accurate Match points
We introduce a novel CNN-based feature point detector - GLAMpoints - learned in a semi-supervised manner.
Ranked #4 on
Image Registration
on FIRE
