Free, simple, and intuitive online database diagram editor and SQL generator.

Picture Manager is a simple image and video viewer with the ability of creating clips from video, tagging faces and editing keywords like rating, people, hierarchical keywords, comments and geo names.

Code for "NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction", NeurIPS 2024

Dark magic delights in Python

A minimal PyTorch implementation of Bundle Adjustment

A differentiable point-based rendering framework.

[CVPR2024(Highlight)] NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

3D目标检测与位姿估计学习笔记

This is a collective repository for all 3DGS related progresses in research and industry world

The source code of the paper "DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction"

Code for SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting built on gsplat codebase.

WildGaussians: 3D Gaussian Splatting In the Wild

SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse views

edition 2 of the slambook

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)

Official implementation of the 2024 ECCV paper SHIC: Shape-Image Correspondences with no Keypoint Annotation

3D高斯论文，持续更新，欢迎交流讨论。

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization (ICLR2024) & DynaVol-S: Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering

Implementation of Continuous Pose for Monocular Cameras in Neural Implicit Representation

PhyRecon: Physically Plausible Neural Scene Reconstruction

Official Implementation for STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians

Superpoint Gaussians Splatting for Real-Time High-Fidelity Monocular Dynamic Scene Reconstruction

[AAAI 2024] PNeRFLoc: Visual Localization with Point-Based Neural Radiance Fields

[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.