Intelligent Systems Lab Org ORG

Open3D: A Modern Library for 3D Data Processing

An open-source library for processing and visualizing 3D data, point clouds, scene reconstruction, surface alignment, and 3D rendering, available as a pip install for Python or as a C++ library, with optional GPU acceleration and ML extensions.

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

Metric depth estimation from a single image

Dense Prediction Transformers

An extension of Open3D to address 3D Machine Learning tasks

Code & Data for Enhancing Photorealism Enhancement

Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"

Language-Driven Semantic Segmentation

Fast Global Registration

Semantic3D segmentation with Open3D and PointNet++

Code repository for "Free View Synthesis", ECCV 2020.

Code repository for "Lagrangian Fluid Simulation with Continuous Convolutions", ICLR 2020.

No description.

Open3D PointNet implementation with PyTorch

Code for Monocular Visual-Inertial Depth Estimation (ICRA 2023)

Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search

Code for the paper "Learning to Act by Predicting the Future", Alexey Dosovitskiy and Vladlen Koltun, ICLR 2017

No description.

Toolbox for the TanksAndTemples benchmark website

Interactive Image Segmentation with Latent Diversity

Adaptive Surface Reconstruction for 3D Data Processing

Repository for the Objects With Lighting Dataset

Find pre-installed Open3D package in CMake

Code for the paper "Accurate Optical Flow via Direct Cost Volume Processing. Jia Xu, René Ranftl, and Vladlen Koltun. CVPR 2017"

No description.

Code to accompany "Does computer vision matter for action?"

[TMLR 2025] Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework

Source code for ICLR 2020 paper: "Learning to Guide Random Search"

Hosting Open3D test data for development use

Simulation and robot code for contact-rich household object insertion (ICRA 2023).

No description.

Use Open3D as a CMake external project

Poisson Surface Reconstruction

No description.

Companion code for the ICML 2022 paper "Generalizing Gaussian Smoothing for Random Search"

Intel GPU accelerated rasterization of gaussian splatting (fork of https://github.com/nerfstudio-project/gsplat)

No description.

[NeurIPS 2024] MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs

Source code for the NeurIPS 2020 Paper: Modeling and Optimization Trade-off in Meta-learning.

Testing Open3D Python package from PyPI and Conda

No description.

Filament is a real-time physically based rendering engine for Android, iOS, Windows, Linux, macOS and WASM/WebGL

Lightning fast differentiable SSIM.

Implementation of CamTrol: Training-free Camera Control for Video Generation

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Forked from https://github.com/dmlc/mshadow

Marching cubes implementation for PyTorch environment.

Markdown to reStructuredText converter

ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes (CoRL 2022)

Intel® RealSense™ SDK

Lets make video diffusion practical!

Generative Omnimatte (CVPR 2025)

This is a python library. Install with "python3 -m pip install rp" then run with "python3 -m rp"

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

MAGI-1: Autoregressive Video Generation at Scale

OctFusion: Octree-based Diffusion Models for 3D Shape Generation

Tame a Wild Camera: In-the-Wild Monocular Camera Calibration

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

No description.

Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)

No description.

No description.

stdgpu: Efficient STL-like Data Structures on the GPU

ZeroMQ core engine in C++, implements ZMTP/3.1

Continuous builder and binary build scripts for pytorch

A library for efficient similarity search and clustering of dense vectors.

Sphinx theme for readthedocs.org