Numair Khan

I am a research scientist at Meta Reality Labs in Redmond, Washington. I work on computer vision and machine learning for applications in computational photography.

I completed my PhD at Brown where I was advised by James Tompkin. I received a Fulbright Scholarship for my Masters at the Courant Institute of New York University where my Master's thesis was advised by Ken Perlin.

Email  /  CV  /  Google Scholar

profile photo
GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis
Yiqing Liang, Numair Khan, Zhenqin Li, Thu Nguyen-Phuoc, Douglas Lanman, James Tompkin, Lei Xiao,
ArXiv, 2024  
arXiv / project page / bibtex

We propose a method for dynamic scene reconstruction based on a deformable set of 3D Gaussians residing in a canonical space, and a time-dependent deformation field defined by a multi-layer perceptron (MLP)

TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
Yu-Ying Yeh, Jia-Bin Huang, Changil Kim, Lei Xiao, Thu Nguyen-Phuoc, Numair Khan, Cheng Zhang, Manmohan Chandrakar, Carl Marshall, Zhao Dong, Zhenqin Li,
ArXiv, 2024  
arXiv / project page / bibtex

We present a novel image-guided texture synthesis method to transfer relightable textures from a small number of input images to target 3D shapes across arbitrary categories.

Tiled Multiplane Images for Practical 3D Photography
Numair Khan, Douglas Lanman, Lei Xiao,
ICCV, 2023  
arXiv / code [coming soon] / bibtex

We propose a method for generating tiled multiplane images with only a small number of adaptive depth planes for single-view 3D photography in the wild.

Temporally Consistent Online Depth Estimation Using Point-Based Fusion
Numair Khan, Eric Penner, Douglas Lanman, Lei Xiao,
CVPR, 2023  
arXiv / code / bibtex

We aim to estimate temporally consistent depth maps of video streams in an online setting by using a global point cloud along with a learned fusion approach in image space.

Neural Fields in Visual Computing and Beyond
Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari James Tompkin Vincent Sitzmann Srinath Sridhar
Eurographics State-of-the-Art Report, 2022
project page / website / arXiv

We present a comprehensive review of neural fields by providing context, mathematical grounding, and an extensive literature review. A companion website contributes a living version that can be continually updated by the community.

Differentiable Diffusion for Dense Depth Estimation from Multi-View Images
Numair Khan Min H. Kim, James Tompkin
CVPR, 2021
project page / code / arXiv / bibtex

A method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision.

Edge-Aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields
Numair Khan, Min H. Kim, James Tompkin
BMVC, 2021
arXiv / project page / code / bibtex

We present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients.

View-Consistent 4D Light Field Depth Estimation
Numair Khan, Min H. Kim, James Tompkin
BMVC, 2020
arXiv / project page / code / bibtex

We propose a method to compute depth maps for every sub-aperture image in a light field in a view-consistent way.

View-Consistent 4D Light Field Superpixel Segmentation
Numair Khan, Qian Zhang, Lucas Kasser, Henry Stone, Min H. Kim, James Tompkin
ICCV, 2019 (Oral Presentation)
paper / code / bibtex

We use occlusion-aware angular segmentation of an Epipolar Plane Image (EPI) to generate light field superpixels that are consistent across views.

Rethinking the Mini-Map: A Navigational Aid to Support Spatial Learning in Urban Game Environments
Numair Khan, Anis Ur Rahman
IJHCI, 2017
paper / bibtex

We propose landmark-based verbal directions as an alternative to mini-maps, and examine the development of spatial knowledge in an open-world urban game environment.

Data Analysis and Call Prediction on Dyadic Data from an Understudied Population
Mehwish Nasim, Aimal Rextin, Shumaila Hayat, Numair Khan, Mudassir Malik
Pervasive and Mobile Computing, 2017
paper / bibtex

Predicting outgoing mobile phone calls using machine learning and time clusters-based approaches.

Space-Efficient Pointwise Computation of the Distance Transform on GPUs
Numair Khan, Mohamed Zahran
International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2017
paper / bibtex

The distance transform is decomposed into a map-and-reduction pattern for efficient computation on GPUs.

Understanding Call Logs of Smartphone Users for Making Future Calls
Mehwish Nasim, Aimal Rextin, Numair Khan, Mudassir Malik
International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI), 2016
paper / bibtex

In this measurement study, we analyze whether mobile phone users exhibit temporal regularity in their mobile communication.

In Search of a Strategy Against Misinformation
I, Entrepreneur
The Essentials of a Computer Scientist's Toolkit
brown-cs Teaching Assistant, CSCI 1290 - Computational Photography, Fall 2020
Teaching Assistant, CSCI 1290 - Computational Photography, Fall 2018
Teaching Assistant, CSCI 2240 - Interactive Computer Graphics, Spring 2018
nust Instructor, Advanced Programming Spring 2016
Instructor, Operating Systems Fall 2015

The source code for this website was copied from Jon Barron's website. It is freely available for personal use here.