Deviant: Depth equivariant network for monocular 3d object detection

A Kumar, G Brazil, E Corona, A Parchami… - European Conference on …, 2022 - Springer
Modern neural networks use building blocks such as convolutions that are equivariant to
arbitrary 2 D translations. However, these vanilla blocks are not equivariant to arbitrary 3 D …

Groomed-nms: Grouped mathematically differentiable nms for monocular 3d object detection

A Kumar, G Brazil, X Liu - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Modern 3D object detectors have immensely benefited from the end-to-end learning idea.
However, most of them use a post-processing algorithm called Non-Maximal Suppression …

On bandlimited field estimation from samples recorded by a location-unaware mobile sensor

A Kumar - IEEE Transactions on Information Theory, 2017 - ieeexplore.ieee.org
Sampling of physical fields with mobile sensor is an emerging area. In this context, this work
introduces and addresses some aspects of a fundamental question: can a spatial field be …

Bandlimited spatiotemporal field sampling with location and time unaware mobile sensors

S Salgia, A Kumar - 2018 IEEE International Conference on …, 2018 - ieeexplore.ieee.org
Sampling of smooth spatiotemporally varying fields is a well-studied topic in the literature.
Classical approach assumes that the field is observed at known sampling locations and …

Estimation of bandlimited signals on graphs from single bit recordings of noisy samples

M Goyal, A Kumar - 2018 26th European Signal Processing …, 2018 - ieeexplore.ieee.org
Recently, there has been interest in graph signal processing. We consider the problem of a
bandlimited graph signal estimation (denoising) from single-bit samples obtained at each …

Dithered A/D Conversion of Bandlimited Signals under Frequency Band Uncertainty

KR Sahasranand - IEEE Signal Processing Letters, 2022 - ieeexplore.ieee.org
We propose a scheme for analog-to-digital (A/D) conversion of a signal that is bandlimited
most of the time but contains harmonics of a high frequency occasionally. To enable the …

Signal Reconstruction From Quantized Noisy Samples of the Discrete Fourier Transform

M Goyal, A Kumar - IEEE Transactions on Signal Processing, 2022 - ieeexplore.ieee.org
In this paper, we present two variations of an algorithm for signal reconstruction from one-bit
or two-bit noisy observations of the discrete Fourier transform (DFT). The one-bit …

Bandlimited spatial field sampling with mobile sensors in the absence of location information

A Kumar - arXiv preprint arXiv:1509.03966, 2015 - arxiv.org
Sampling of physical fields with mobile sensor is an emerging area. In this context, this work
introduces and proposes solutions to a fundamental question: can a spatial field be …

On transmission of a continuous signal via a noiseless binary channel

N Dokuchaev - IEEE Signal Processing Letters, 2015 - ieeexplore.ieee.org
We study the problem of the transmission of currently observed time variable signals via a
channel that is capable of sending a single binary signal only for each measurement of the …

Spatial Field estimation from Samples taken at Unknown Locations generated by an Unknown Autoregressive Process

S Salgia, A Kumar - arXiv preprint arXiv:1710.09451, 2017 - arxiv.org
Sampling of physical fields with mobile sensors is an upcoming field of interest. This offers
greater advantages in terms of cost as often just a single sensor can be used for the purpose …