ophilar

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

DeepSpeedExamples

Example models using DeepSpeed

multinerf

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

tiny-cuda-nn

Lightning fast C++/CUDA neural network framework

input-leap

Open-source KVM software

mitsuba3

Mitsuba 3: A Retargetable Forward and Inverse Renderer

mmflow

OpenMMLab optical flow toolbox and benchmark

cv-arxiv-daily

🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)

bundle-adjusting-NeRF

BARF: Bundle-Adjusting Neural Radiance Fields 🤮 (ICCV 2021 oral)

SegmentAnyRGBD

Segment Any RGBD

silk

SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.

DF-VO

Depth and Flow for Visual Odometry

IGEV

[CVPR 2023] Iterative Geometry Encoding Volume for Stereo Matching and Multi-View Stereo

ENeRF

SIGGRAPH Asia 2022: Code for "Efficient Neural Radiance Fields for Interactive Free-viewpoint Video"

OnePose_Plus_Plus

Code for "OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models" NeurIPS 2022

idisc

iDisc: Internal Discretization for Monocular Depth Estimation [CVPR 2023]

tartanvo

TartanVO: A Generalizable Learning-based VO

DIM-SLAM

This is official repo for ICLR 2023 Paper "DENSE RGB SLAM WITH NEURAL IMPLICIT MAPS"

DeepMapping2

[CVPR2023] DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization

DeFlowSLAM

code for "DeFlowSLAM: Self-Supervised Scene Motion Decomposition for Dynamic Dense SLAM"

softpool

SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification - ECCV 2020 oral

LSDIR

GliTr

GliTr Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction

SIRST-Single-Point-Supervision

hybrid3d