#
Starred repositories
178
stars
written in Python
Clear filter
ROS Wrapper for Intel(R) RealSense(TM) Cameras
Plenoxels: Radiance Fields without Neural Networks
[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Simultaneous object detection and tracking using center points.
Unsupervised single image depth prediction with CNNs
Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
Schedule-Free Optimization in PyTorch
A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.
PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)
Non-local Neural Networks for Video Classification
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
Official implementation of "Implicit Neural Representations with Periodic Activation Functions"
Atlas: End-to-End 3D Scene Reconstruction from Posed Images
Slides and other materials from CppCon 2017
We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
Pyramid Stereo Matching Network (CVPR2018)
[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
[ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
gradslam is an open source differentiable dense SLAM library for PyTorch
[TPAMI'23] Unifying Flow, Stereo and Depth Estimation
Freedoom is an entirely free software game based on the Doom engine.