Showing papers by "K. S. Venkatesh published in 2022"

Occlusion Resistant Network for 3D Face Reconstruction

Abstract: 3D face reconstruction from a monocular face image is a mathematically ill-posed problem. Recently, we observed a surge of interest in deep learning-based approaches to address the issue. These methods possess extreme sensitivity towards occlusions. Thus, in this paper, we present a novel context-learning-based distillation approach to tackle the occlusions in the face images. Our training pipeline focuses on distilling the knowledge from a pre-trained occlusion-sensitive deep network. The proposed model learns the context of the target occluded face image. Hence our approach uses a weak model (unsuitable for occluded face images) to train a highly robust network towards partially and fully-occluded face images. We obtain a landmark accuracy of 0.77 against 5.84 of recent state-of-the-art-method for real-life challenging facial occlusions. Also, we propose a novel end-to-end training pipeline to reconstruct 3D faces from multiple variations of the target image per identity to emphasize the significance of visible facial features during learning. For this purpose, we leverage a novel composite multi-occlusion loss function. Our multi-occlusion per identity model shows a dip in the landmark error by a large margin of 6.67 in comparison to a recent state-of-the-art method. We deploy the occluded variations of the CelebA validation dataset and AFLW2000-3D face dataset: naturally-occluded and artificially occluded, for the comparisons. We comprehensively compare our results with the other approaches concerning the accuracy of the reconstructed 3D face mesh for occluded face images.

Self-Supervised Cooperative Colorization of Achromatic Faces

Abstract: Despite the recent progress in deep learning-based face image colorization techniques, there is still much room for improvement. One of the significant challenges is the bias toward specific skin color. Moreover, the conventional face colorization approaches aim to produce colored 2D face images, whereas the generation of colored 3D faces from monocular achromatic (gray-scale) images is beyond the scope of these methods despite having immense potential applications. To address these issues, we propose Self-Supervised COoperative COlorizaTion of Achromatic Faces (COCOTA) framework that contains chromatic and achromatic pipelines to jointly estimate the color and shape of 3D faces using monocular achromatic face images without inducing any specific color bias. On the challenging CelebA test dataset, COCOTA out-performs the current state-of-the-art method by a large margin (e.g., for 3D color-based error, a reduction from 5.12 ± 0.13 to 3.09 ± 0.08 leading to an improvement of 39.6%), demonstrating the effectiveness of the proposed method.

Reduced Dependency Fast Unsupervised 3D Face Reconstruction

Abstract: Recent 3D face reconstruction methods show encouraging results in retrieving 3D face shape and texture from monocular face images. However, these approaches pose several dependencies during testing, such as the requirement of facial landmark coordinates. Moreover, a large testing time presents a challenge for real-time applications. To address these issues, we propose REduced Dependency Fast UnsuperviSEd 3D Face Reconstruction (RED-FUSE) framework, which uses unprocessed face images to estimate reliable 3D face shape and texture, thus eliminating the need for prior land-mark knowledge, and considerable prediction time during testing. RED-FUSE outperforms the current state-of-the-art method on CelebA dataset e.g., for 3D shape and color-based errors, a reduction from 5.84 ± 0.16 to 3.14 ± 0.11 and from 3.50 ± 0.14 to 2.97 ± 0.09 is observed, leading to an improvement of 46.2% and 15.1%, respectively. In addition, the testing time reduces from 7.30 msec to 1.85 msec per face, showing the effectiveness of our method.

Neural Network Based Landing Assist Using Remote Sensing Data

Abstract: This paper presents the application of computer vision and artificial neural networks for autonomous approach and landing and taxiing for an aircraft. In civil aviation and unmanned aircraft system industry, safety has always been the prime concern. We present a system which uses modern pattern recognition algorithm to aid in the landing of all types of aerial vehicles. The auto-land systems used today in aviation sector utilize a radio waves-based system known as Instrument Landing System (ILS) which has been in operation since decades. Although, it is efficient but might sometime be intermittent and is vulnerable to interference.Moreover, the auto-land system works in conjunction with different devices such as radio altimeter, ILS, Global Positioning System (GPS) and others. But, before reaching the Minimum Decision Altitude (MDA), pilots are expected to have the runway threshold marking, aiming point marking, displacement arrows and other touchdown markings/lights in-sight for landing. For this purpose, use of imaging sensors as an augmentation system for pilots during landing can improve the safety manifolds. Our method uses modern artificial neural networks to learn to recognize and localize important visual references during landing and taxiing useful for pilots by utilizing the satellite imagery dataset from Google Earth Engine (GEE) cloud computing.