minhaj ansari - Academia.edu (original) (raw)
Uploads
Papers by minhaj ansari
ArXiv, 2021
Deep learning based 3D reconstruction of single view 2D image is becoming increasingly popular du... more Deep learning based 3D reconstruction of single view 2D image is becoming increasingly popular due to their wide range of real-world applications, but this task is inherently challenging because of the partial observability of an object from a single perspective. Recently, state of the art probabilitybased Occupancy Networks reconstructed 3D surfaces from three different types of input domains: single view 2D image, point cloud and voxel. In this study, we extend the work on Occupancy Networks by exploiting cross-domain learning of image and point cloud domains. Specifically, we first convert the single view 2D image into a simpler point cloud representation, and then reconstruct a 3D surface from it. Our network, the Double Occupancy Network (D-OccNet) outperforms Occupancy Networks in terms of visual quality and details captured in the 3D reconstruction.
Sensors are finding more prominent role in today’s world. They used in everyday objects such as e... more Sensors are finding more prominent role in today’s world. They used in everyday objects such as environmental monitoring, medical diagnostic, health care, automobile, industry manufacturing, defence and security. This paper gives a brief review of the sensors based on nanomaterials. The unique properties of nanomaterials play a significant role in the development of sensors. The use of innovative nanomaterials is expected to result in sensors products which substantially enhanced sensitivity, selectivity, decrease in power consumption and excellent reproducibility.
ArXiv, 2021
Deep learning based 3D reconstruction of single view 2D image is becoming increasingly popular du... more Deep learning based 3D reconstruction of single view 2D image is becoming increasingly popular due to their wide range of real-world applications, but this task is inherently challenging because of the partial observability of an object from a single perspective. Recently, state of the art probabilitybased Occupancy Networks reconstructed 3D surfaces from three different types of input domains: single view 2D image, point cloud and voxel. In this study, we extend the work on Occupancy Networks by exploiting cross-domain learning of image and point cloud domains. Specifically, we first convert the single view 2D image into a simpler point cloud representation, and then reconstruct a 3D surface from it. Our network, the Double Occupancy Network (D-OccNet) outperforms Occupancy Networks in terms of visual quality and details captured in the 3D reconstruction.
Sensors are finding more prominent role in today’s world. They used in everyday objects such as e... more Sensors are finding more prominent role in today’s world. They used in everyday objects such as environmental monitoring, medical diagnostic, health care, automobile, industry manufacturing, defence and security. This paper gives a brief review of the sensors based on nanomaterials. The unique properties of nanomaterials play a significant role in the development of sensors. The use of innovative nanomaterials is expected to result in sensors products which substantially enhanced sensitivity, selectivity, decrease in power consumption and excellent reproducibility.