Pablo Vela's repositories
arxiv-researcher
Summarize any Arixv Paper with ease
dn-splatter
DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing
ml-coursera-python-assignments
Python assignments for the machine learning class by andrew ng on coursera with complete submission for grading capability and re-written instructions.
AnchorHODL
Anchor Protocol Script that can save you from being liquidated!
dust3r
DUSt3R: Geometric 3D Vision Made Easy
grounding-sam
Demo combining Grounding DINO with SAM (Segment Anything Model) visualized with Rerun
HandOccNet
Offical pytorch implementation of "HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network", CVPR 2022.
Hierarchical-Localization
Visual localization made easy with hloc
I2L-MeshNet_RELEASE
Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020
instant-nsr-pl
Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!
mediapipe-1
Cross-platform, customizable ML solutions for live and streaming media.
mini-omnidata
Minimal omnidata for arbitrary resolution images
MobileBrick
This repository contains evaluation code for CVPR2023 paper "MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices"
nerfstudio
A collaboration friendly studio for NeRFs
OS-Bot-COLOR
A lightweight desktop client & toolkit for writing, controlling and monitoring color-based automation scripts.
Segment-and-Track-Anything
An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
simplerecon
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
SplaTAM
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM