Junshan Huang's starred repositories
SGG-Benchmark
A New Benchmark for Scene Graph Generation, targeting real-world applications
Depth-Anything-V2
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Objectron
Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes
HyperbolicCV
ICLR 2024 | Fully Hyperbolic Convolutional Neural Networks for Computer Vision | Official Implementation
Deformable-DETR
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
blind_watermark
Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！
mc_auto_boss
鸣潮后台自动刷BOSS声骸
easy-gpt4o
Easy-GPT4O opensource version
NBodySimulation
N-body simulation based on CUDA.
better-genshin-impact
📦BetterGI · 更好的原神 - 自动拾取 | 自动剧情 | 全自动钓鱼(AI) | 全自动七圣召唤 | 自动伐木 | 自动刷本 | 自动采集 - UI Automation Testing Tools For Genshin Impact
ProgrammingVTuberLogos
High-quality PNGs for logos I made for fun
capture-courses
USTC在线视频平台录课访问
BIG-Bench-Mistake
A dataset of LLM-generated chain-of-thought steps annotated with mistake location.
Digital_Life_Server
Yet another voice assistant, but alive.