Stars
NetVLAD: CNN architecture for weakly supervised place recognition
Driver and tools for controlling Lenovo Legion laptops in Linux including fan control and power mode.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Adds AMD FSR 3 Frame Generation to games by replacing Nvidia DLSS Frame Generation (nvngx_dlssg).
OptiScaler bridges upscaling/frame gen across GPUs. Supports DLSS2+/XeSS/FSR2+ inputs, replaces native upscalers, enables FSR3 FG on non-FG titles. Supports Nukem mod for DLSSG-to-FSR3 FG.
ShadowFormer (AAAI2023), Pytorch implementation
openMVG with a LATCH descriptor, an ORB descriptor, DEEP descriptors from the cvpr15compare repo, PNNet/Torch loader and a GPU-based L2 matcher integrated
Python package for the evaluation of odometry and SLAM
open Multi-View Stereo reconstruction library
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
An optimization-based multi-sensor state estimator
OKVIS: Open Keyframe-based Visual-Inertial SLAM.
A Robust and Versatile Monocular Visual-Inertial State Estimator
This is BundleFusion for Ubuntu version
Shellscript to compile git with OpenSSL
Using traditional image processing techniques to construct 3D point cloud of objects. Incremental Structure from Motion (SfM) is used, a popular SfM algorithm for 3D reconstruction for reconstructi…
[Siggraph 2017] BundleFusion: Real-time Globally Consistent 3D Reconstruction using Online Surface Re-integration
There is five robot in a formation who is doing its task. They can communicate with each other by a communication topology and correct their position. And they realized obstacle avoidance by using …
Fault-tolerant formation control using energy tanks
FOC for stm32\esp32-pico with many different drivers