3D vision · neural rendering · data systems

Neham Jain

Researcher working on 3D foundation models, reconstruction systems, and the data infrastructure that makes geometric learning practical at scale.

01 Scene Reconstruction

Smoke-free 3D Gaussian splatting for difficult real-world scenes.

02 Data Engines

Scalable curation, QA, and training pipelines for multimodal models.

03 Robotic Perception

Geometry, sensing, and learning systems that survive contact with reality.

About Me

Hi, my name is Neham, I am currently a Researcher at Meshy.ai, where I am working on 3D foundation models and data. Previously, I was a Research Engineer at Meta Reality Labs, building large scale multi-modal data pipelines and data curation for training foundation models. I graduated with a Master of Science in Robotics from Carnegie Mellon University in May 2025, where I was fortunate to be advised by Prof. Ioannis Gkioulekas and collaborate with Prof. Sebastian Scherer. My thesis was titled “SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstruction”.

Prior to CMU, I earned my Bachelor of Technology in Electrical Engineering from IIT Madras with a Minor in Machine Learning.

I am always open to academic and engineering discussions and potential collaborations. Feel free to reach out to me at nehamjain2002 [at] gmail.com


Research and Engineering Interests

  • 3D Computer Vision & Neural Rendering
  • Scalable Data Pipelines & Curation
  • Robotic Perception
  • Multimodal Learning
  • Deep Learning Systems & CUDA Optimization

News and Updates

  • May 2026: Gave a talk at Voxel51’s seminar series!
  • March 2026: Started as a Researcher at Meshy.ai, working on 3D foundation models and data!
  • Winter 2025: SmokeSeer accepted as a poster at 3DV 2026! [Supplementary Results]
  • Fall 2025: Embody3D a large-scale multimodal motion and behavior dataset released!
  • June 2025: Started as Research Engineer at Meta Reality Labs!
  • May 2025: Graduated with MS in Robotics from CMU!
  • Summer 2024: Research internship at Adobe Research, San Francisco — built scalable 3D foundation model pipeline
  • Spring 2024: Paper accepted at WWW 2024 — Counterfactual Explanations for Visual Recommender Systems