activity
20192022
most citedDeceiving Image-to-Image Translation Networks for Autonomous Driving with Adversarial Perturbations

29 citations · 59 across the 7 of their papers we have counts for

collaborators

9 papers

cs.CV20223 cited

Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge

Kyeongseob Song, Kuk-Jin Yoon

Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods. To tackl…

cs.CV20228 cited

Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks

Pranjay Shyam, Sandeep Singh Sengar, Kuk-Jin Yoon +1

The limited dynamic range of commercial compact camera sensors results in an inaccurate representation of scenes with varying illumination conditions, adversely affecting image qua…

cs.CV20223 cited

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang +5

Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and expl…

cs.CV20222 cited

DGSS : Domain Generalized Semantic Segmentation using Iterative Style Mining and Latent Representation Alignment

Pranjay Shyam, Antyanta Bangunharcana, Kuk-Jin Yoon +1

Semantic segmentation algorithms require access to well-annotated datasets captured under diverse illumination conditions to ensure consistent performance. However, poor visibility…

cs.CV20218 cited

Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks

Pranjay Shyam, Sandeep Singh Sengar, Kuk-Jin Yoon +1

Region modification-based data augmentation techniques have shown to improve performance for high level vision tasks (object detection, semantic segmentation, image classification,…

cs.CV20216 cited

Towards Domain Invariant Single Image Dehazing

Pranjay Shyam, Kuk-Jin Yoon, Kyung-Soo Kim

Presence of haze in images obscures underlying information, which is undesirable in applications requiring accurate environment information. To recover such an image, a dehazing al…