High-Resolution Image Synthesis with Latent Diffusion Models

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

pySLAM contains a monocular Visual Odometry (VO) pipeline in Python. It supports many modern local features based on Deep Learning.

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Code and data for "SeMLaPS: Real-time Semantic Mapping with Latent Prior Networks and Quasi-Planar Segmentation"

🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.

DUSt3R + Gaussian Splatting

Tensorflow port of https://github.com/Relja/netvlad

Code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition"

Pytorch implementation of NetVlad including training on Pittsburgh.

End-to-end learning of deep visual representations for image retrieval

A curated list of awesome visual localization research works.

Level of Gaussians

[ECCV 2024] RGBD GS-ICP SLAM

Gaussian Opacity Fields: Efficient and Compact Surface Reconstruction in Unbounded Scenes

Tutorial for building a custom CUDA function for Pytorch

[ICCV 2023] PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

[CVPR'24, Demo Track Honourable Mention] SuperPrimitive: Scene Reconstruction at a Primitive Level

Official implementation for SlimmeRF: Slimmable Radiance Fields (3DV 2024 Best Paper)

Wrapper for g2o python bindings

DUSt3R: Geometric 3D Vision Made Easy

Code for "GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting"

[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM

Example pybind11 module built with a Python-based build system

Python binding for ORB-SLAM3.

[CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis