Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation

2 code implementations • CVPR 2021 • Youngmin Oh, Beomjun Kim, Bumsub Ham

We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations.

Object Segmentation +2

Deformable Kernel Networks for Joint Image Filtering

2 code implementations • 17 Oct 2019 • Beomjun Kim, Jean Ponce, Bumsub Ham

Previous methods based on convolutional neural networks (CNNs) combine nonlinear activations of spatially-invariant kernels to estimate structural details and regress the filtering result.

Depth Map Super-Resolution Image Restoration +1

Deformable kernel networks for guided depth map upsampling

no code implementations • 27 Mar 2019 • Beomjun Kim, Jean Ponce, Bumsub Ham

We address the problem of upsampling a low-resolution (LR) depth map using a registered high-resolution (HR) color image of the same scene.