Search Results for author: Madhu Vankadari

Found 5 papers, 2 papers with code

Tighter Variational Bounds are Not Necessarily Better. A Research Report on Implementation, Ablation Study, and Extensions

1 code implementation23 Sep 2022 Amine M'Charrak, Vít Růžička, Sangyun Shin, Madhu Vankadari

We provide theoretical and empirical evidence that increasing the number of importance samples $K$ in the importance weighted autoencoder (IWAE) (Burda et al., 2016) degrades the signal-to-noise ratio (SNR) of the gradient estimator in the inference network and thereby affecting the full learning process.

Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR

no code implementations21 Sep 2022 Sangyun Shin, Stuart Golodetz, Madhu Vankadari, Kaichen Zhou, Andrew Markham, Niki Trigoni

Supervised approaches typically require the annotation of large training sets; there has thus been great interest in leveraging weakly, semi- or self-supervised methods to avoid this, with much success.

3D Object Detection object-detection +1

When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation

no code implementations28 Jun 2022 Madhu Vankadari, Stuart Golodetz, Sourav Garg, Sangyun Shin, Andrew Markham, Niki Trigoni

In this paper, we show how to use a combination of three techniques to allow the existing photometric losses to work for both day and nighttime images.

Depth Estimation Motion Estimation

Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation

1 code implementation ECCV 2020 Madhu Vankadari, Sourav Garg, Anima Majumder, Swagat Kumar, Ardhendu Behera

We propose to solve this problem by posing it as a domain adaptation problem where a network trained with day-time images is adapted to work for night-time images.

Depth Prediction Domain Adaptation +3

Cannot find the paper you are looking for? You can Submit a new open access paper.