Cheng Wang

Cheng Wang

About

Publications

Projects

Experience

Cheng Wang 王呈

chengwang@ucsd.edu

About Me

Hi! I'm Cheng Wang, a second-year Master student in Computer Science at UC San Diego, advised by Prof. Tzu-Mao Li. I received my Bachelor's degree in Computer Science and Technology at Chu Kochen College of Zhejiang University, advised by Prof. Rui Wang. During my academic journey, I developed a strong passion for visual computing, particularly interested in physically-based rendering and inverse rendering. I am motivated to leverage technology to enhance people's lives, making them happier and more convenient.

I was a Software Engineer Intern at Electronic Arts and a Rendering Engine Engineer Intern at Rays Engine. Please feel free to take a look at my CV.

Skills

C/C++

Python

PyTorch

Rust

Unreal Engine 5

OpenGL

CUDA

TypeScript

Next.js

SwiftUI

Interests

Badminton

Chess

Classical Music

Cooking

Computer Games

Publications

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Ruoxi Shi, Xinyue Wei, Cheng Wang, Hao Su

A novel per-scene optimization method addressing the challenge of sparse view 360° reconstruction in neural field representations.

Selected Projects

Volumetric Path Tracing

I implemented volumetric path tracing that can handle multiple chromatic heterogeneous volumes with absorption and multiple-scattering, with both phase function sampling and next event estimation, based on an educational physically-based renderer, lajolla.

Implementation of Tensorial Radiance Field (TensoRF) with PyTorch

I implemented Tensorial Radiance Field (TensoRF) following the work of Chen et al. TensoRF represents a radiance field by matrix-vector and vector-vector combinations of tensors. Compared to MLP based NeRF, it is more efficient while preserving comparable quality without customized CUDA implementation.

Real-Time Texture-Space Subsurface Scattering

I applied a new, efficient method which performs convolution of radiance map and weight kernel in texture space. By pre-calculating weight kernels with Burley's normalized diffusion profile and applying wavelet transformation, the method significantly reduced time complexity of convolution.

Awarded the Outstanding Graduation Thesis of Zhejiang University Undergraduates in 2022.

Tiled Forward Shading

I implemented tiled forward rendering and tiled deferred rendering according to existing papers, and optimized light culling pass by using multiple frustum dividing and light-frustum intersection strategies. Afterwards, I conducted experiments to compare the performance of the strategies mentioned above. Finally I transplanted the algorithms aborementioned to android devices.

We designed and implemented a 3D computer game resembling Assassin's Creed with Unreal Engine 4.

Worked in a group of five I mainly focused on scene and level design, enemy animation and behavior design, special effect design based on particle system, etc. And I assisted to complete other modules in the game.

Medical Appointment System

I led a 20-people team and developed a hospital website based on Vue.js and Java, whose main functions including information viewing, registration appointment, online consultation, video diagnosis, online forum, etc.

I participated in front-end programming, back-end programming and the design and maintenance of the cloud database.

Petiu: Pet farewell service system

Worked in a group of three, I designed and developed IOS App "Petiu" with SwiftUI.

We attended China Collegiate Computing Contest -- Mobile Application Innovation Contest held by Apple Inc. and Zhejiang University in 2021, and were awarded Third Prize.

Experience

2022 - Present

M.S. in Computer Science

University of California San Diego, CA, United States

2023

Software Engineer Intern

Electronic Arts, CA, United States

2021 - 2022

Rendering Engine Engineer Intern

RaysEngine, Zhejiang, China

2018 - 2022

B.E. in Computer Science and Technology

Zhejiang University, Zhejiang, China

© Cheng Wang. All Rights Reserved.