Vision and AI Laboratory (VAL) -- IISc

This project is an implementation of the Generative Adversarial Network proposed in our CVPR 2017 paper - DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data. DeLiGAN is a simple bu...

val-iisc

val-iisc

Repository for 3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image [BMVC 2018]

val-iisc

This project is an implementation of the crowd counting model proposed in our CVPR 2017 paper - Switching Convolutional Neural Network(SCNN) for Crowd Counting. SCNN is an adaptation of the fully-conv...

val-iisc

Generalized Data-free Universal Adversarial Perturbations

val-iisc

Code, demos and data for SketchParse (a neural network for sketch segmentation). Paper:

val-iisc

Data independent universal adversarial perturbations

val-iisc

Visualising predictions of deep neural networks

val-iisc

Repository for 3D-PSRNet: Part Segmented 3D Point Cloud Reconstruction [ECCVW 2018]

val-iisc

Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes

val-iisc