01
Neuromorphic Imaging
Spike cameras sample light continuously instead of in frames. I build the reconstruction stack that turns those sub-millisecond binary streams back into colour, high-dynamic-range video.
Tokyo, JapanLocal--:--:--
Ph.D. Candidate in Computer Science at the Camera Intelligence Lab, Peking University. I work on spike cameras.inverse rendering.world models.light & pixels.
01 — About
Light, sampled differently.
I teach cameras to see what human eyes cannot — microsecond-scale light, recovered as colour, motion and geometry.
My research sits between computational photography and computer vision: neuromorphic spike cameras that fire asynchronously at tens of thousands of frames per second, inverse rendering that pulls material and illumination back out of a photograph, and generative world models that render playable video.
Before the Ph.D. I spent a decade in competitive programming, which is probably why I still enjoy a well-shaped abstraction more than a well-tuned hyperparameter.
- Research Intern
- Shanda AI Research, Tokyo
- Building
- Multiplayer world models & panoramic video generation
- Learning
- Nix, Rust, and how to take better photographs
- Graduating
- July 2027 (expected)
02 — Focus
Three questions I keep returning to.
Different sensors, one problem: recovering the physical world from the light it happens to send us.
02
Inverse Rendering
Given a photograph, recover the scene that made it — geometry, reflectance, and the light that fell on it — so the whole thing can be relit and re-photographed.
03
World Models
Video generators that hold a consistent, controllable, and shared state, so more than one person can walk around inside the same generated world.
03 — Path
Where I have been.
- 2025 — Nowexperience
Shanda AI Research
Research Intern · Tokyo, Japan
Multiplayer world models, panoramic video generation, generative game platform.
- 2022 — 2027education
Peking University
Ph.D. in Computer Science · Beijing, China
Camera Intelligence Lab, advised by Prof. Boxin Shi and Prof. Zhaofei Yu.
- 2019experience
Hyperplane Lab, Peking University
Research Intern · Beijing, China
Convolutional neural network quantisation and pruning.
- 2018 — 2022education
Peking University
B.S. in Computer Science · Beijing, China
Turing Honor Class, School of EECS.
- 2018experience
Youtu X-Lab, Tencent
Research Intern · Shenzhen, China
Object detection and classification on the Tencent Weishi dataset.
04 — Work
Selected publications.
14 papers across CVPR, ICCV, ECCV, NeurIPS, SIGGRAPH Asia and TPAMI.
- 2026MASS: Multiplayer World Models with Authoritative Shared State
- 2026High-Speed Full-Color HDR Imaging via Unwrapping Modulo-Encoded Spike Streams
- 2025PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms
- 2025SpikeDiff: Zero-shot High-Quality Video Reconstruction from Chromatic Spike Camera and Sub-Millisecond Spike Streams
- 2024Real-Data-Driven 2000 FPS Color Video from Mosaicked Chromatic Spikes
- 2023Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting
- 2026Generative World Renderer at the Speed of Play
- 2026InstructAV2AV: Instruction-Guided Audio-Video Joint Editing
- 2026Interactive Panoramic World Exploration via Camera Control
- 2026HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly Rotating SpokeND Filter
- 2026Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner
- 2025EventUPS: Uncalibrated Photometric Stereo Using an Event Camera
- 2024Focal Stack and Light Field Imaging
- 2023MILO: Multi-bounce Inverse Rendering for Indoor Scene with Light-emitting Objects
05 — Recognition
Medals, mostly from problems.
- 2025PKU–Huawei Turing Graduate Program Scholarship
- 2025Huawei Hackathon, Software ChallengeGold Medal
- 2019Peking University Academic Excellence Award
- 2018China Collegiate Programming Contest, GuilinGold Medal
- 2017National Olympiad in Informatics (NOI)Silver Medal
- 2016–2017NOIP First Prize ×2 · APIO / CTSC / WCBronze Medals
Academic Service
Conference Reviewer
- CVPR
- ICCV
- ECCV
- NeurIPS
- SIGGRAPH
- ACCV
- PRCV
- ICIG
Journal Reviewer
- TPAMI
Toolkit
06 — Toolkit
Languages
Python · C++ · CUDA · Rust · TypeScript · Lisp · Nix
Deep Learning
PyTorch · JAX · TensorFlow · Diffusers · Triton
Graphics & Imaging
NeRF · 3DGS · Differentiable Rendering · Spike Sensor Pipeline
Infrastructure
Docker · Ray · Cloudflare · GCP · Git
07 — Contact