Niladri Shekhar Dutt

prof_pic.jpg

I am a first year ELLIS PhD student at University College London (UCL), sponsored by Adobe Research. I am fortunate to be advised by Prof Niloy Mitra (UCL) and Duygu Ceylan (Adobe). My current research focuses on multimodal learning, combining MLLMs with computer graphics and vision for reasoning in generative and procedural modeling tasks.

past

Research Intern @ Nvidia, Visiting scholar @ Berkeley, Research Engineer @ Ready Player Me, Founding Engineer @ NFTPort (raised $26M, now Galadriel)

news


publications

  1. monetGPT.jpg
    MonetGPT: Solving Puzzles Enhances MLLMs’ Image Retouching Skills
    Niladri Shekhar Dutt, Duygu Deylan, and Niloy Mitra
    SIGGRAPH (ACM Transactions on Graphics, conditional accept), 2025
  2. diff3f.jpg
    Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features
    Niladri Shekhar Dutt, Sanjeev Muralikrishnan, and Niloy Mitra
    CVPR, 2024
  3. smf.jpg
    SMF: Template-free and Rig-free Animation Transfer using Kinetic Codes
    Sanjeev Muralikrishnan*Niladri Shekhar Dutt*, and Niloy Mitra
    preprint, 2025
  4. flairgpt.gif
    FlairGPT: Repurposing LLMs for Interior Designs
    Gabrielle Littlefair, Niladri Shekhar Dutt, and Niloy Mitra
    Eurographics, 2025
  5. trj.jpg
    Temporal Residual Jacobians for Rig-Free Motion Transfer
    Sanjeev Muralikrishnan, Niladri Shekhar Dutt, Siddhartha Chaudhuri, and 4 more authors
    ECCV, 2024
  6. proteus.gif
    Proteusnerf: Fast Lightweight NeRF Editing using 3D-Aware Image Context
    Binglun Wang, Niladri Shekhar Dutt, and Niloy Mitra
    ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D), 2024