AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Official implementation of NeurIPS'2021 paper TransformerFusion

[CVPR 2023] Code for "VisFusion: Visibility-aware Online 3D Scene Reconstruction from Videos"

GPT4 based personalized ArXiv paper assistant bot

A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation for Indoor Scene.

PyTorch Quantization Aware Training(QAT,量化感知训练)

Code for our CVPR 2023 paper on online, temporally consistent depth estimation.

[CVPR 2021] Self-supervised depth estimation from short sequences

Align depth image to color image manually

Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral

[ECCV 2024] DoubleTake: Geometry Guided Depth Estimation

Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)

Glances an Eye on your system. A top/htop alternative for GNU/Linux, BSD, Mac OS and Windows operating systems.

pipreqs - Generate pip requirements.txt file based on imports of any project. Looking for maintainers to move this project forward.

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

GLOMAP - Global Structured-from-Motion Revisited

This repo accompanies the research paper, ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data and contains the data, scripts to visualize and proces…

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

Muggled DPT: Depth estimation without the magic

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Algorithm to texture 3D reconstructions from multi-view stereo images

Python logging made (stupidly) simple

Google Drive Public File Downloader when Curl/Wget Fails

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

Atlas: End-to-End 3D Scene Reconstruction from Posed Images

[ECCV 2024] Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation