Jhon Edinson Lopez Duran

Ph.D. Candidate in Computer Science · Universidad Industrial de Santander · expected graduation April 2027

I work on computer vision, computational imaging, generative AI and AI safety. I build vision systems that people can trust: cameras that protect your identity from the moment a photo is taken, images that can prove they are real, and generative models whose results can be checked. My goal is an AI era where we can trust what we see and feel safe when we are seen.

CV Email Scholar GitHub LinkedIn
Jhon Edinson Lopez Duran
CVPR 2026Oral · NOWA
CVPR 2024First author
EMNLP 2026First author · SGA
ICIP 2022Best Paper Award
69 citationsh-index 5 · Google Scholar
Selected research

What I work on

All research →
NOWA pipeline: a phase mask in the camera embeds a null-space watermark used to localize tampering
CVPR 2026 · OralRice University

NOWA: Null-space Optical Watermark

A phase mask in the camera aperture hides a watermark in the null space of the optics: invisible in the photo, but it fingerprints the capture and localizes tampering. Validated on a prototype camera.

Paper →arXiv →
Traditional camera versus privacy-preserving camera with an optimized phase mask
CVPR 2024First author

Privacy-Preserving Optics for Face De-identification

Camera optics learned jointly with a network so that identity is removed at capture time, before the image is digitized, while the image stays useful for downstream vision. Core of my PhD.

Project page →Paper →arXiv →
SGA overview: symbolic geometric verification of LLM-generated animation code
EMNLP 2026First author

SGA: Geometric Verification for Educational Video

A plug-and-play agent that checks LLM-generated Manim code for spatial overlaps on a symbolic scene graph and fixes them before rendering. Raters preferred it over the raw output in 84% of comparisons.

Project page →arXiv →
MambaStyle inversion and editing results on faces and cars
arXiv 2025First author

MambaStyle: Efficient StyleGAN Inversion

A single-stage encoder built on vision state-space models for real-image inversion and editing, with fewer parameters and faster inference than state-of-the-art encoders.

arXiv →
Learned color-coded apertures mounted on camera lenses
IEEE TCI 2024ECCV 2024 Workshops

Coded Apertures for Depth Estimation

Color and binary coded apertures learned end-to-end with a depth network, recovering depth from a single coded image or a low-cost stereo pair, tested on lab prototypes.

TCI paper →ECCVW paper →
News

Recent updates

  • SGA accepted at EMNLP 2026 (Budapest, Oct 24–29). Project page

  • SGA released on arXiv, in collaboration with KAUST.

  • NOWA presented as an Oral at CVPR 2026 (Session 1B: Visual Security, Denver).

  • NOWA accepted at CVPR 2026 as an Oral presentation.

  • MambaStyle released on arXiv.

Background

Experience & education

Research experience

  • Research Intern (on-site, two stays)

    Rice University · Computational Imaging Lab
    Houston, TX · most recently Apr – Oct 2025 · Prof. Ashok Veeraraghavan

    Optical methods for image authenticity: co-developed NOWA (CVPR 2026 Oral) and built and calibrated phase-mask camera prototypes.

  • Research Intern (virtual)

    KAUST
    Prof. Bernard Ghanem · Dr. Carlos Hinojosa

    SGA (EMNLP 2026) and MambaStyle.

  • Graduate Researcher

    HDSP Group · Universidad Industrial de Santander
    2020 – present · Prof. Henry Arguello

    Learned coded apertures, lenses and networks for depth, scene captioning and face de-identification, with coded-aperture, stereo and deformable-mirror lab setups.

Education

  • Ph.D. in Computer Science

    Universidad Industrial de Santander
    2022 – 2027 · expected graduation April 2027

    Thesis: Optical Privacy System Design to Enhance Human De-identification. Advisor: Prof. Henry Arguello.

  • M.Sc. in Computer Science

    Universidad Industrial de Santander
    2020 – 2022

  • B.Sc. in Computer Science

    Universidad Industrial de Santander
    2015 – 2020
Recognition

Awards & fellowships

  • 2026Oral presentation, CVPR 2026 (NOWA)
  • 2022Best Paper Award, IEEE ICIP 2022
  • 2023 – 2026Merit-Based Doctoral Fellowship, Universidad Industrial de Santander
  • 2020 – 2022Merit-Based Graduate Fellowship, Universidad Industrial de Santander
  • 2015 – 2020Ser Pilo Paga Scholarship, ICETEX (national merit scholarship)
Community

Service & talks

  • ReviewerCVPR, ICCV, ECCV, IEEE TPAMI, IEEE TCI
  • Oct 2026EMNLP 2026, Budapest: SGA
  • Jun 2026CVPR 2026, Denver: NOWA (Oral)