• Publications
  • Influence
CBAM: Convolutional Block Attention Module
The proposed Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks, can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. Expand
Adaptive Support-Weight Approach for Correspondence Search
A new window-based method for correspondence search using varying support-weights based on color similarity and geometric proximity to reduce the image ambiguity and outperforms other local methods on standard stereo benchmarks. Expand
Multispectral pedestrian detection: Benchmark dataset and baseline
This dataset introduces multispectral ACF, which is an extension of aggregated channel features (ACF) to simultaneously handle color-thermal image pairs, and achieves another breakthrough in the pedestrian detection task. Expand
High quality depth map upsampling for 3D-TOF cameras
This paper describes an application framework to perform high quality upsampling on depth maps captured from a low-resolution and noisy 3D time-of-flight (3D-ToF) camera that has been coupled with aExpand
Accurate depth map estimation from a lenslet light field camera
This paper introduces an algorithm that accurately estimates depth maps using a lenslet light field camera and estimates the multi-view stereo correspondences with sub-pixel accuracy using the cost volume using the phase shift theorem. Expand
BAM: Bottleneck Attention Module
A simple and effective attention module, named Bottleneck Attention Module (BAM), that can be integrated with any feed-forward convolutional neural networks, that infers an attention map along two separate pathways, channel and spatial. Expand
Partial Sum Minimization of Singular Values in Robust PCA: Algorithm and Applications
Instead of minimizing the nuclear norm, this paper proposes to minimize the partial sum of singular values, which implicitly encourages the target rank constraint, and shows that its results outperform those obtained by the conventional nuclear norm rank minimization method. Expand
A Tensor-Based Algorithm for High-Order Graph Matching
The proposed approach to establishing correspondences between two sets of visual features using higher order constraints instead of the unary or pairwise ones used in classical methods is compared to state-of-the-art algorithms on both synthetic and real data. Expand
EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images
This paper introduces a fast and accurate light field depth estimation method based on a fully-convolutional neural network that achieved the top rank in the HCI 4D Light Field Benchmark on most metrics, and demonstrates the effectiveness of the proposed method on real-world light-field images. Expand
DPSNet: End-to-end Deep Plane Sweep Stereo
A convolutional neural network called DPSNet (Deep Plane Sweep Network) whose design is inspired by best practices of traditional geometry-based approaches for dense depth reconstruction, achieves state-of-the-art reconstruction results on a variety of challenging datasets. Expand