Anagh Malik

I am a second year Computer Science PhD student at the University of Toronto, supervised by David Lindell. I am affiliated with both the Toronto Computational Imaging Group and the Vector Institute.

Before this I did my MRes at the Dyson Robotics Lab at Imperial College London, where I worked on self-supervised segmentation, under the supervision of Andrew Davison and Ronald Clark.

Email:
anagh [at] cs [dot] toronto [dot] edu


Twitter  /  Resume /  Google Scholar /  GitHub

profile photo
Research

I am broadly interested in scene understanding. That is using visual cues to infer properites of objects and scenes.

Transientangelo: Few-Viewpoint Surface Reconstruction Using Single-Photon Lidar
Weihan Luo, Anagh Malik, David B. Lindell
WACV, 2025
project page / arXiv / code

Few-view surface reconstruction using single-photon lidar data.

Flying with Photons: Rendering Novel Views of Propagating Light
Anagh Malik, Noah Juravsky, Ryan Po, Gordon Wetzstein, Kiriakos N. Kutulakos, David B. Lindell
ECCV, 2024   (Oral Presentation)
project page / video / arXiv / code

Novel view synthesis of arbitrary light propagation videos - including effects such as scattering or interreflections.

Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction
Anagh Malik, Parsa Mirdehghan, Sotiris Nousias, Kiriakos N. Kutulakos, David B. Lindell
NeurIPS, 2023   (Spotlight)
project page / video / arXiv / code

We introduce a method to do novel view lidar synthesis, allowing sparse view scene reconstruction.

clean-usnob Exploring Neural Representations for Self-Supervised Segmentation
Anagh Malik
Master's Thesis, 2022

We develop a method for self-supervised segmentation through agreement and self-distillation.

clean-usnob SegDIP: The Unreasonable Effectiveness of Randomly-Initialized CNNs for Interactive Segmentation
Anagh Malik, Shuaifeng Zhi, Marwan Taher, Ronald Clark, Andrew Davison
Technical Report 2021

We train an encoder-decoder network to map from xy-coordinates to RGB values and semantic classes, allowing real-time segmentation of an image.


Template stolen from Jon Barron's website.