Akshay Krishnan

prof_pic.jpg

Hi! I am a PhD student at Georgia Tech, advised by Prof. James Hays. My research is in Spatial AI, I train models to generate and reconstruct interactive virtual 3D environments from images. I am currently also a research intern at Waymo. I enjoy working at the intersection of diffusion models, 3D geometry, and optimization.

I’ve been fortunate to intern with some outstanding teams at Google DeepMind, Niantic Spatial, and Blue River Technology. Before starting my PhD, I worked on long-range perception at Waymo. During my Master’s program, I was introduced to SfM (and 3D vision) at Prof. Frank Dellaert’s group. I was also part of a wonderful team from the RAIL lab that won the FetchIt! challenge at ICRA 2019.

I have served as a reviewer for CVPR 2025, ICCV 2025, NeurIPS 2026, BMVC 2026, and RA-L. Please feel free to email me if you’re interested in research collaborations!

Selected Publications

  1. crossviewsplatter.png
    Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images
    Matias Turkulainen , Akshay Krishnan , Filippo Aleotti , Mohamed Sayed , Guillermo Garcia-Hernando , Juho Kannala , Arno Solin , Gabriel Brostow , and Daniyar Turmukhambetov
    In Computer Vision and Pattern Recognition (CVPR) , 2026
    arXiv HTML
  2. orchid_preview.jpg
    Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation
    Akshay Krishnan , Xinchen Yan , Vincent Casser , and Abhijit Kundu
    In International Conference on Computer Vision (ICCV) , 2025
    arXiv HTML
  3. omninocs.gif
    OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects
    Akshay Krishnan , Abhijit Kundu , Kevis-Kokitsi Maninis , James Hays , and Matthew Brown
    In European Conference on Computer Vision (Oral) , 2024
    arXiv HTML Code
  4. gtsfm.gif
    Distributed Global Structure-from-Motion with a Deep Front-End
    Ayush Baid , John Lambert , Travis Driver , Akshay Krishnan , Hayk Stepanyan , and Frank Dellaert
    arXiv, 2023
    arXiv Code
  5. lane.gif
    LANe: Lighting-Aware Neural Fields for Compositional Scene Synthesis
    Akshay Krishnan , Amit Raj , Xianling Zhang , Alexandra Carlson , Nathan Tseng , Sandhya Sridhar , Nikita Jaipuria , and James Hays
    arXiv, 2023
    arXiv HTML
  6. fetchit.jpg
    Taking Recoveries to Task: Recovery-Driven Development for Recipe-based Robot Tasks
    Siddhartha Banerjee , Angel Andres Daruna , Cassandra Kent , Weiyu Liu , Jonathan C. Balloch , Abhinav Jain , Akshay Krishnan , Muhammad Asif Rana , Harish Ravichandar , Binit Shah , and 2 more authors
    In International Symposium of Robotics Research , 2020
    arXiv