Kunal Gupta

I’m a PhD candidate in computer science at UC San Diego, advised by Manmohan Chandraker. I study how AI agents can learn from human creative judgment. When a filmmaker adjusts a camera or a material artist revises a shader, what can an agent learn from the choices that led to the final result?

I build agents that use creative software and produce work people can edit. My current research explores how agents can use Unreal Engine and DaVinci Resolve to stage, shoot, and edit a scene. My background is in 3D vision, neural rendering, and geometry, including research at Adobe and NVIDIA. I earned my MS at UC San Diego and my BE at BITS Pilani, and received a Qualcomm Innovation Fellowship in 2023.

I’m on the job market for early 2027. I’m looking for a full-time Research Scientist or Member of Technical Staff role at a startup or industry research lab. I’d love to hear from teams working on agents, computer use, simulation, or creative tools. Email me.

Email / Resume / Google Scholar / GitHub / LinkedIn

Selected publications

Research overview · Full publication list

	Material Apprentice: Reflecting Process Expertise in Procedural Material Generation Kunal Gupta, Gaurav Joshi, Yen-Ru Chen, Seemandhar Jain, Ishit Mehta, Manmohan Chandraker ECCV 2026 Paper / Project page An agent learns from artists’ demonstrations to build editable procedural materials in Blender.
	NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code Seemandhar Jain, Keshav Gupta, Kunal Gupta, Manmohan Chandraker CVPR 2026 · Highlight Paper / Project page Agents turn research papers into trainable Nerfstudio plugins and use visual feedback to debug their implementations.
	InteriorAgent: LLM Agent for Interior Design-Aware 3D Layout Generation Kunal Gupta, Ishit Mehta, Kun Wang, Nicholas Chua, Abhimanyu Krishna, Yan Deng, Ravi Ramamoorthi, Manmohan Chandraker 3DV 2026 Paper / Project page An agent lays out 3D rooms in Blender, reasoning about how people move through a space and how the furnishings fit together.
	MCNeRF: Monte Carlo Rendering and Denoising for Real-Time NeRFs Kunal Gupta, Miloš Hašan, Zexiang Xu, Fujun Luan, Kalyan Sunkavalli, Xin Sun, Manmohan Chandraker, Sai Bi ACM SIGGRAPH ASIA 2023 paper / project page / arXiv / code A general Monte Carlo-based method to accelerate the rendering of any NeRF representation.
	Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes Noam Aigerman, Kunal Gupta, Vladimir Kim, Siddhartha Chaudhuri, Jun Saito, Thibault Groueix ACM SIGGRAPH 2022 (journal track) Paper / code A framework for learning to deform meshes in a highly detail-preserving manner, without being tied to a specific mesh
	DiFiR-CT: Distance Field Representation resolves motion during Computed Tomography Kunal Gupta, Brendan Colvert Zhennong Chen and Francisco Contijoch Medical Physics 2023 paper / project page / arXiv / code Motion resolved computed tomography by combining neural implicit representations and differentiable rendering
	Motion Correction Image Reconstruction using NeuralCT Improves with Spatially Aware Object Segmentation Zhennong Chen, Kunal Gupta, Francisco Contijoch 7th International Conference on Image Formation in X-Ray Computed Tomography, 2022 Paper and code
	Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows Kunal Gupta, Manmohan Chandraker NeurIPS 2020 (Spotlight) project page / arXiv / code / Master's Thesis A network that generates manifold meshes enabling photo-realistic physically based renderings and physics simulation
	Force Control of Robotic Walker Bachelor's Thesis Novel Stable Gait Criteria (SGC) is proposed for safe and intuitive human-robot interaction and rehabilitation.

Talks

Random Walks and Sampling at MC Lab Discussions, September 2020

ELBO and KL-Divergence Tutorial at ERL Discussions, December 2018

Template stolen from Jon Barron

Questions about graduate study at UC San Diego? Read my FAQ.