• Publications
  • Influence
Joint Recovery of Dense Correspondence and Cosegmentation in Two Images
We propose a new technique to jointly recover cosegmentation and dense per-pixel correspondence in two images. Our method parameterizes the correspondence field using piecewise similarity
Neural Inverse Rendering for General Reflectance Photometric Stereo
TLDR
A physics based unsupervised learning framework where surface normals and BRDFs are predicted by the network and fed into the rendering equation to synthesize observed images, which is shown to achieve the state-of-the-art performance on a challenging real-world scene benchmark.
Continuous 3D Label Stereo Matching Using Local Expansion Moves
TLDR
This new move-making scheme is used to efficiently infer per-pixel 3D plane labels on a pairwise Markov random field (MRF) that effectively combines recently proposed slanted patch matching and curvature regularization terms.
Graph Cut Based Continuous Stereo Matching Using Locally Shared Labels
TLDR
An accurate and efficient stereo matching method using locally shared labels, a new labeling scheme that enables spatial propagation in MRF inference using graph cuts, and the selection and propagation of locally-defined disparity labels as fusion-based energy minimization are presented.
Semi-global Stereo Matching with Surface Orientation Priors
TLDR
This paper evaluates plane orientation priors derived from stereo matching at a coarser resolution and shows that such priors can yield significant performance gains for difficult weakly-textured scenes.
Fast Multi-frame Stereo Scene Flow with Motion Segmentation
TLDR
A new multi-frame method for efficiently computing scene flow and camera ego-motion for a dynamic scene observed from a moving stereo camera rig, where the method consistently outperforms OSF, which is currently ranked second on the KITTI benchmark.
Continuous Stereo Matching using Local Expansion Moves
TLDR
An accurate and efficient stereo matching method using local expansion moves, a new move making scheme using graph cuts, that can efficiently infer Markov random field models with a huge or continuous label space using a randomized search scheme.
Path Planning using Neural A* Search
TLDR
This work reformulates a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end trainable neural network planner that outperformed state-of-the-art data-driven planners in terms of the search optimality and efficiency trade-off.
Superdifferential cuts for binary energies
TLDR
This work presents their method as generalization of SSP, which is further shown to generalize several state-of-the-art techniques for higher-order and pairwise non-submodular functions.
Neural Photometric Stereo Reconstruction for General Reflectance Surfaces
TLDR
A reconstruction based unsupervised learning framework where surface normals and BRDFs are predicted by the network and fed into the rendering equation to synthesize observed images, which is shown to achieve the state-of-the-art performance on a challenging real-world scene benchmark.
...
...