-
CUHK
- Hong Kong, China
-
09:36
(UTC +08:00) - https://wbhu.github.io/
- @wbhu_cuhk
- in/huwenbo
Lists (3)
Sort Name ascending (A-Z)
Stars
llms 大模型 笔记50篇 此仓库包含关于机器学习、深度学习、计算机视觉、自然语言处理、大模型 爬虫等领域 项目实战
source code for our work "CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting"
A tool for exploring each layer in a docker image
SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"
Official implementation of the paper “MagicDriveDiT: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”
Video classification tools using 3D ResNet
[CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis
High Resolution Depth Maps for Stable Diffusion WebUI
Simple custom node pack for nodes I use in my workflows.
A refactored codebase for Gaussian Splatting. Faster!! Modular!! Pure Python or CUDA Extension
[3DV 2025] Official Implementation of paper "Photometric Inverse Rendering: Shading Modeling and Surface Reflectance Regularization"
Unifying 3D Mesh Generation with Language Models
Simple script to parallelize download and extract files for SA-1B Dataset.
A visionOS app that lets you control a toy rocket with a game controller.
Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
A suite of image and video neural tokenizers
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
A Synthetic Immersive Large-Volume Plenoptic Dataset
Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data", CVPR 2024; 3D Avatar Generation and Animation