most citedFCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

14 citations · 14 across the 1 of their papers we have counts for

collaborators

3 papers

cs.CV2017★ 14 cited

FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

Seungryong Kim, Dongbo Min, Bumsub Ham +3

We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic correspondence. To robustly match points among different instances within the same ob…

cs.CV2016

Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields

Seungryong Kim, Kihong Park, Kwanghoon Sohn +1

We present a method for jointly predicting a depth map and intrinsic images from single-image input. The two tasks are formulated in a synergistic manner through a joint conditiona…

cs.CV2016

Deep Self-Convolutional Activations Descriptor for Dense Cross-Modal Correspondence

Seungryong Kim, Dongbo Min, Stephen Lin +1

We present a novel descriptor, called deep self-convolutional activations (DeSCA), designed for establishing dense correspondences between images taken under different imaging moda…