Education
Relevant Coursework: Probabilistic Artificial Intelligence, Computational Photography, Unsupervised Learning, Virtual Reality Technology, Structured Prediction for NLP, Sampling and Reconstruction of Visual Appearance: From Denoising to View Synthesis, Deep Generative Models.
Relevant Courses: Artificial Intelligence, Machine Learning, Data Warehousing and Data Mining, Data Structures and Algorithms, Natural Language Processing
Experience
Developed a training free 3D face editing method for Generative NeRFs & obtained realistic 3D face edits for eyeglasses & age. Rendered dataset of 10K+ 3D faces from 2D images. Developed large-scale distributed ML training pipelines of upto 256 GPUs.
Investigated CRTF based sub-surface scattering in NeRFs for translucent objects with 10% improvement in novel view synthesis. Working on inverse rendering algorithms for physics-based face relighting with sub-surface scattering effects from 2D images.
Led development of TEGLO: a novel Generative NeRF for 3D reconstruction from single view images obtaining ≥74 db PSNR (≥200% improvement) over state of the art preserving fine details at megapixel resolutions [Under Review].
Simplified feature modifications in VW by implementing a reduction for data modification functions to register on the stack. Enabled on-the-fly feature manipulations for contextual bandit learning without requiring re-deploying the source.
Obtained ≥12% improvement over state-of-the-art in few-shot domain adaptation for RAW image enhancement in low light conditions for DSLR & smartphone cameras with new benchmark data [BMVC 2021, Best Student Paper Runner Up] Led the development of a self-supervised image translation method to translate daylight scenes to rain/fog/night and enabled a 5% improvement in image segmentation performance for self-driving cars in adverse weather [ICCV 2021, ILDAV]
Implemented state-of-the-art ML models for TensorFlow mentored by Jaeyoun Kim, Hongkun Yu and Yanhui Liang from Google Brain.Led the development of FineGAN, a fine-grained image generation method with hierarchical disentanglement using TensorFlow. Investigated SIREN with implicit representation networks and evaluated the expressivity of Batchnorm for deep networks.
Implemented StackGAN: text-to-image Generative Adversarial Network (GAN) with two-stage image super-resolution using TF2. TF Model Garden: Built StackGAN, Mask R-CNN, Conditional VAE, and Face Aging with CycleGANs from the research papers.
Worked on "RainRoof: Automated Shared Rainwater Harvesting Prediction" under the guidance of Dr. Savita Choudhary (Springer LNDECT). Also worked on "Forecasting Dengue and Studying its Plausible Pandemy" under the guidance of Prof. Savita Choudhary (Elsevier). Worked on "Predicting the Network Structure using Harmonic Centrality Values in AODV Routing for Wireless Sensor Networks" under the guidance of Dr. Pallavi Venkatesh and Dr. Banu Prakash (SSN IJSTR 2019).
Publications
-
TEGLO: High Fidelity Canonical Texture Mapping from Single-View Images.
Vishal Vinod, Tanmay Shah, Dmitry Lagun
ArXiv 2023
Paper Website -
Few-Shot Domain Adaptation for Low Light RAW Image Enhancement
K. Ram Prabhakar, Vishal Vinod, Nihar Sahoo, R. Venkatesh Babu, Anirban Chakraborty
32nd British Machine Vision Conference (BMVC 2021)
[Best Student Paper Award - Runner-Up] -
Multi-Domain Conditional Image Translation: Translating
Driving Datasets from Clear-Weather to Adverse Conditions
Vishal Vinod, K. Ram Prabhakar, R. Venkatesh Babu, Anirban Chakraborty
IEEE/CVF International conference on Computer Vision (ICCV 2021) Workshop -
Estimating Leaf Water Content using Remotely Sensed
UAV-captured Hyperspectral Data
Vishal Vinod, Rahul Raj, Rohit Pingale, Adinarayana Jagarlapudi
IEEE/CVF International conference on Computer Vision (ICCV 2021) Workshop -
Leaf Water Content Estimation using Top-of-Canopy
Airborne Hyperspectral Data
Rahul Raj, Jeffrey Walker, Vishal Vinod, Rohit Pingale, Balaji Naik, Adinarayana Jagarlapudi
International Journal of Applied Earth Observation and Geoinformation (JAG) -
Mining Intelligent Patterns using SVAC for Precision
Agriculture and Optimizing Irrigation (SA)
Vishal Vinod, Vipul Gaurav, Tushar Sharma, Savita Choudhary
AAAI Conference on Artificial Intelligence (AAAI 2021) -
Towards Efficient Computer Vision Models for Challenging
Scenarios in Urban Mobility
Vishal Vinod, Savita Choudhary
AAAI Conference on Artificial Intelligence (AAAI 2021), UM Workshop -
RainRoof: Automated Shared Rainwater Harvesting
Prediction
Vishal Vinod*, Vipul Gaurav*, Tushar Sharma, Sanyam Singh, Savita Choudhary
Springer Lecture Notes in Data Engineering and Communication Technologies -
Predicting Harmonic Centrality in AODV Routing for
Wireless Sensor Networks.
Pallavi R, Vishal Vinod, Tushar Sharma, G C Bhanu Prakash
International Journal of Scientific and Technological Research
Select Projects
- Implemented the 3-Stage FineGAN Architecture with a stage each for Background, Foreground Outline and Foreground Mask generation.
- This includes the Background scene detector to detect background only patches for the auxiliary discriminator trained on CUB200.
- Language agnostic translation with BioBERT question-answer heads training the embedding layers and generative pre-training. Used GPT-2 for generative pre-training for natural language answer generation for medical queries followed by translation.
- Results from the NLG architecture for health intelligence is under review at the AAAI 2021.
- Model created from the paper to train StackGAN on the CUB 200 dataset for birds. Includes the 2 stages in the model. Stage 1 takes the latent space and a conditioning vector as input to generate 64x64 resolution images. (With Char-RNN-CNN).
- The Stage 2 generates 256x256 resolution images from Stage 1 images.
AI Summer School
EEML summer school is focused on core topics regarding machine learning and artificial intelligence. The summer school includes both lectures and practical sessions (labs) to improve the theoretical and practical understanding of these topics. The school is aimed at graduate students. Participated in the Continual Learning track.
AI School to investigate and comprehend the limitations of the machine learning models and make them more fair, transparent and accountable. This school addresses some fundamental and pressing topics in fairness, accountability and transparency in AI.
Topics covered in the summer school broadly include comprehensive sessions on Machine Learning, AI, Knowledge Graphs, NLP, Game Theory, Discrete Mathematics, Linear Algebra, and Advanced Databases. Interactions with the professors was very engaging.