Repository Index

TRI-ML Monocular Depth Estimation Repository

Cuckoo Filter: Practically Better Than Bloom

Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)

Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

• language-modeling
• natural-language-generation
• machine-learning
• deep-learning

Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)

Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)

• tensorflow
• matconvnet
• depth-maps
• depth-prediction

HyperLogLog with lots of sugar (Sparse, LogLog-Beta bias correction and TailCut space reduction) brought to you by Axiom

• axiom
• data-structures
• go
• golang

"Neural Turing Machine" in Tensorflow

• tensorflow
• neural-turing-machines

Implementation of Tightly Coupled 3D Lidar Inertial Odometry and Mapping (LIO-mapping)

• sensor-fusion
• slam
• mapping
• icra2019

SuMa++: Efficient LiDAR-based Semantic SLAM (Chen et al IROS 2019)

• rangenet-lib
• suma
• lidar
• slam

AI-IMU Dead-Reckoning

• imu
• state-estimation
• inertial-odometry
• localization

Gibson Environments: Real-World Perception for Embodied Agents

• computer-vision
• robotics
• simulator
• sim2real

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018

• pytorch
• deep-learning
• generative-adversarial-network
• trajectory-prediction

TensorFlow Implementation of "Show, Attend and Tell"

• tensorflow
• image-captioning
• show-attend-and-tell
• attention-mechanism

RNNLIB is a recurrent neural network library for sequence learning problems. Forked from Alex Graves work http://sourceforge.net/projects/rnnl/

OpenFE: automated feature generation with expert-level performance

CubeSLAM: Monocular 3D Object Detection and SLAM

• slam

QuadriFlow: A Scalable and Robust Method for Quadrangulation

• quadriflow
• quad
• remeshing
• quadrangulation

🏅State-of-the-art learned data structure that enables fast lookup, predecessor, range searches and updates in arrays of billions of items using orders of magnitude less space than traditional indexes

• data-structures
• database
• cpp
• research

C++ implementation of a fast and memory efficient HAT-trie

• cpp
• trie
• hat-trie
• data-structures

TensorFlow Implementation of Unsupervised Cross-Domain Image Generation

• tensorflow
• domain-transfer
• unsupervised-learning
• image-generation

Code for "High-Precision Model-Agnostic Explanations" paper

vibe coded supermimic within 1h, LAFAN passed within 1.5 gpuh training

HairDeck: Animation-Ready Stylized Hair Cards from a Single Image