Stars
MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
[CVPR 2024] GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
Train your AI self, amplify you, bridge the world
[CVPR 2025 Best Paper Award Candidate] VGGT: Visual Geometry Grounded Transformer
Xiaomi watchfaces editor for various watch, band models by Xiaomi
Xiaomi watchfaces examples running on LUA engine, Mi Band 8 Pro, Mi Watch S3 models
Pretraining code for a large-scale depth-recurrent language model
Code for reproducing experiments in "On the Ability of Graph Neural Networks to Model Interactions Between Vertices"
Repository for effective resistance sampling code to create network sparsifiers.
Python code associated with the paper "A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarsening'' (NeurIPS, 2019)
[IJCAI 2024] Papers about graph reduction including graph coarsening, graph condensation, graph sparsification, graph summarization, etc.
Multilevel graph coarsening algorithm with spectral and cut guarantees
End-to-end SFM framework based on GTSAM
lucasbrynte / gasfm
Forked from drormoran/Equivariant-SFMImplementation of the CVPR 2024 paper "Learning Structure-from-Motion with Graph Attention Networks".
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
Helpful tools and examples for working with flex-attention
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
Run macOS on QEMU/KVM. With OpenCore + Monterey + Ventura + Sonoma support now! Only commercial (paid) support is available now to avoid spammy issues. No Mac system is required.