Tianyi Zhang | 张天仪

Ph.D.

Email CV Scholar Github

Update: I joined Aurora and work with Dr. Kronander and Dr. Wrenninge on team MLTA🇲🇹 (Machine Learning Training & Analysis) and team SWSS🇨🇭 (Synthetic World & Sensor Simulation).

Hi! My name is Tianyi . I'm a ~~Ph.D. student~~ (Done) in Robotics at CMU advised by Prof. Matthew Johnson-Roberson. My research lies in 3D computer vision including physics-based reconstruction, diffusion models, simulation, and 3D foundation models that enable robots to better localize, navigate, and understand their environment. I also do hardware design and prototype especially for robot perception systems.

NEWS & Media Coverage: Our work featured by NOAA.gov (2023); The LINK (Spring 2024); CMU News (May 2024); CMU News (Nov 2024);

Research

DreamSea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models

Tianyi Zhang , Weiming Zhi , Joshua Mangelson , Matthew Johnson-Roberson

ICRA 2026; FM-Wild@ICLR 2025

paper bibtex Oral Presentation @ FM-Wild

DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark

Tianyi Zhang , Kaining Huang , Weiming Zhi , Matthew Johnson-Roberson

IROS 2024

paper code bibtex website video Oral Presentation

Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery

Tianyi Zhang , Matthew Johnson-Roberson

RA-L 2023, ICRA 2024

paper code bibtex video

More Research & Projects (19)

RecGS: Removing Water Caustic with Recurrent Gaussian Splatting

Tianyi Zhang , Weiming Zhi , Braden Meyers , Nelson Durrant , Kaining Huang , Joshua Mangelson , Corina Barbalata , Matthew Johnson-Roberson

RA-L 2024, ICRA 2025

paper code bibtex website

Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization

Tianyi Zhang , Matthew Johnson-Roberson

RA-L 2022, ICRA 2022

paper code bibtex

Features in the Point Cloud: An Automatic Approach to High Density LiDAR to Camera Calibration

Tianyi Zhang , Eduardo Iscar , Matthew Johnson-Roberson

Research report for M.S. Robotics degree, University of Michigan

paper

PhotoReg: Photometrically Registering 3D Gaussian Splatting Models

Ziwen Yuan , Tianyi Zhang , Matthew Johnson-Roberson , Weiming Zhi

IROS 2026

website paper

One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

Xiaohao Xu , Feng Xue , Xiang Li , Haowei Li , Shusheng Yang , Tianyi Zhang , Matthew Johnson-Roberson , Xiaonan Huang

ECCV 2026

paper code data video bibtex Spotlight

Bi-Manual Joint Camera Calibration and Scene Representation

Haozhan Tang , Tianyi Zhang , Matthew Johnson-Roberson , Weiming Zhi

ICRA 2026

paper website

Efficient Construction of Implicit Surface Models From a Single Image for Motion Generation

Wei-Teng Chu , Tianyi Zhang , Matthew Johnson-Roberson , Weiming Zhi

ICRA 2026

paper code website

Building 3D Representations and Generating Motions From a Single Image via Video-Generation

Weiming Zhi , Ziyong Ma , Tianyi Zhang , Matthew Johnson-Roberson

NeurIPS 2025

paper

DOSE3: Diffusion-Based Unified Out-of-Distribution Detection on SE(3) Trajectories

Hongzhe Cheng , Tianyou Zheng , Ziyong Ma , Tianyi Zhang , Matthew Johnson-Roberson , Weiming Zhi

RA-L 2025

paper

Unified Self-supervised Representation Learning for Multi-modal and Single-modal 3D Perception

Xiaohao Xu , Ye Li , Tianyi Zhang , Jinrong Yang , Matthew Johnson-Roberson , Xiaonan Huang

CASE 2025

paper code

Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video

Xiaohao Xu , Tianyi Zhang , Shibo Zhao , Xiang Li , Sibo Wang , Yongqi Chen , Ye Li , Bhiksha Raj , Matthew Johnson-Roberson , Sebastian Scherer , Xiaonan Huang

ICLR 2025

paper bibtex code website

RS-ModCubes: Self-Reconfigurable, Scalable, Modular Cubic Robots for Underwater Operations

Jiaxi Zheng , Guangmin Dai , Botao He , Zhaoyang Mu , Zhaochen Meng , Tianyi Zhang , Weiming Zhi , Dixia Fan

RA-L 2025; IROS 2025

paper website

Teaching Periodic Stable Robot Motion Generation via Sketch

Weiming Zhi , Haozhan Tang , Tianyi Zhang , Matthew Johnson-Roberson

RA-L 2024, ICRA 2025

paper

Simultaneous Geometry and Pose Estimation of Held Objects via 3D Foundation Models

Weiming Zhi , Haozhan Tang , Tianyi Zhang , Matthew Johnson-Roberson

RA-L 2024, ICRA 2025

paper

Embodied-RAG: General non-parametric Embodied Memory for Retrieval and Generation

Quanting Xie , So Yeon Min , Tianyi Zhang , Aarav Bajaj , Ruslan Salakhutdinov , Matthew Johnson-Roberson , Yonatan Bisk

Under Review

website paper

Unifying Representation and Calibration with 3D Foundation Models

Weiming Zhi , Haozhan Tang , Tianyi Zhang , Matthew Johnson-Roberson

RA-L 2024, ICRA 2025

paper bibtex

Teaching Robots Where To Go and How To Act with Human Sketches via Spatial Diagrammatic Instructions

Qilin Sun , Weiming Zhi , Tianyi Zhang , Matthew Johnson-Roberson

IROS 2024

paper bibtex

Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis

Hu et al.

arxiv | in submission

paper bibtex

Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching

Weiming Zhi , Tianyi Zhang , Matthew Johnson-Roberson

ICRA 2024

paper Spotlight - IROS 2023 DiffPropRob Workshop

Field Work

Novel-view rendering of an underwater scene with NeRF

Novel-view rendering with NeRF

Florida Keys Aug 2023

Hawaii Sea Oct 2019

Education

Ph.D. Robotics, Carnegie Mellon University (CMU)
2022-2025

M.S. Robotics, University of Michigan, Ann Arbor (UM)
2018-2020

B.Eng. Tianjin University (TJU)

Work Experience

Software Engineer, Aurora (2025-present)
Data-driven sensor simulation.

$Refraction AI logo$

Software Engineer, Refraction AI (2019)
Automated Camera-LiDAR-IMU calibration for a delivery robot.

Visiting Undergrad Researcher, Massachusetts Institute of Technology (2018)

Donut Eater & Software Intern, SLAMTEC (2017 Summer)
SLAMTEC builds really good LiDARs and robot platforms. Check it out!

Teaching

Graduate Student Instructor    ROB535 Self-driving Cars: Perception and Control, Fall 2021, UMich
Teaching Assistant    16664 Self-driving Cars: Perception and Control, Spring 2023, CMU
Teaching Assistant    16385 Computer Vision, Fall 2023, CMU

Services

Reviewer: T-RO, RA-L, CoRL, ECCV, ICRA, IROS, KDD, NeurIPS, WACV

Thanks Pedro Morgado for this amazing template.

Back to the top.