Wuziyi616

Graduate_Application

Documents used for grad school application

CFUN

Combining Faster R-CNN and U-net for efficient medical image segmentation

SlotDiffusion

Code release for NeurIPS 2023 paper SlotDiffusion: Object-centric Learning with Diffusion Models

multi_part_assembly

Code Accompany NeurIPS 2022 Dataset Paper: Breaking Bad. A Shape Assembly Benchmark Implemented in PyTorch

IF-Defense

This is the official pytorch implementation for paper: IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration

LEOD

Code release for CVPR 2024 paper LEOD: Label-Efficient Object Detection for Event Cameras

Artificial_Intelligence_Project1

Project1 for 2019 Autumn class: An Introduction to Artificial Intelligence, Department of Automation, Tsinghua University. A Tangram Puzzle Solver.

nerv

Personal Python toolbox

Personal_CV

My personal CV

SlotFormer

Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models

EDC20_Team_A_star_strategy_part

The strategy board code for the EDC20, THU championship team A_star

EventCLIP

Code release for paper EventCLIP: Adapting CLIP for Event-based Object Recognition

mmdetection3d

OpenMMLab's next-generation platform for general 3D object detection.

Wuziyi616.github.io

Personal Website

Computer_Network_Project

Final Project for 2019 Autumn class: Computer Network, Department of Automation, Tsinghua University. A chatting software.

ngp_pl

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

Numerical_Analysis_Project1

Project1 for 2019 Autumn class: Numerical Analysis, Department of Automation, Tsinghua University. An image and a face morpher.

Wuziyi616

CLIP

Contrastive Language-Image Pretraining

kubric

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

PeRFception

Official implementation of PeRFception: Perception using Radiance Fields.