-
Samsung Research America
- Mountain View
- https://www.linkedin.com/in/nbansal009?trk=hp-identity-name
Stars
A library for efficient similarity search and clustering of dense vectors.
one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment
Python library to download bulk of images from Bing.com
We write your reusable computer vision tools. π
This repository contains the official implementation of the research paper, "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" CVPR 2024
[TPAMI'23] NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction
Provides end-to-end model development pipelines for LLMs and Multimodal models that can be launched on-prem or cloud-native.
A list of recent papers, libraries and datasets about 3D shape/scene analysis (by topics, updating).
Chamfer Distance in Pytorch with f-score
Continuous Remeshing For Inverse Rendering
A collection of resources and papers on Diffusion Models
Benchmarking PyTorch variants of TSDF fusion.
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
π A list of awesome scene understanding papers.
Stable Diffusion web UI
A curated list of awesome computer vision resources
Paper reading notes on Deep Learning and Machine Learning
This will contain my notes for research papers that I read.
π A study guide to learn about Graph Neural Networks (GNNs)
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
README and scripts for the Cityscapes Dataset
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)
An adversarial example library for constructing attacks, building defenses, and benchmarking both
[NeurIPS '18] "Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?" Official Implementation.