Top Repositories
Neural implicit surface modelling. Fast, efficient implementation of NeuS with Instant-NGP's hash grid encoding, and CUDA-accelerated components.
Code repository for the paper "InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video", presented at Asian Conference on Computer Vision (ACCV) 2024.
My own NumPy-based implementation of a multilayer perceptron (MLP). Several of its components can be tuned and played with, such as layer depth and size, hidden and output layer activation functions, weight decay and dropout.
Current hand pose estimation methods are often unreliable and do not always produce estimations with enough quality. To mitigate this issue, we explore the applicability of the novel Body2Hands method for the obtainment of high-quality hand pose estimations.
Here you can find a small PySpark project that performs an ETL from some data in csv format in order to prepare it for prediction. In particular, the data corresponds to air-flights and the task is to predict, given an aircraft, if it is going to have an unscheduled maintenance.
Repositories
24Neural implicit surface modelling. Fast, efficient implementation of NeuS with Instant-NGP's hash grid encoding, and CUDA-accelerated components.
Code repository for the paper "InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video", presented at Asian Conference on Computer Vision (ACCV) 2024.
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
No description provided.
No description provided.
Analyzing the Capabilities of Visual Recognition Systems in Autonomous Driving and in Out-of-Domain Scenarios
Video Surveillance for Road Traffic Monitoring project within Module 6: Video Analysis of the Master's program in Computer Vision at UAB.
We perform 3D reconstruction of buildings from sets of images of urban scenes taken from different points of view.
No description provided.
Code release for NeuS
Unifying Flow, Stereo and Depth Estimation
[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
No description provided.
Offical code for the paper: "Growing 3D Artefacts and Functional Machines with Neural Cellular Automata" https://arxiv.org/abs/2103.08737
Notes I took about some of the chapters in book Elements of Statistical Learning.
My own NumPy-based implementation of a multilayer perceptron (MLP). Several of its components can be tuned and played with, such as layer depth and size, hidden and output layer activation functions, weight decay and dropout.
Current hand pose estimation methods are often unreliable and do not always produce estimations with enough quality. To mitigate this issue, we explore the applicability of the novel Body2Hands method for the obtainment of high-quality hand pose estimations.
Here you can find a small PySpark project that performs an ETL from some data in csv format in order to prepare it for prediction. In particular, the data corresponds to air-flights and the task is to predict, given an aircraft, if it is going to have an unscheduled maintenance.
A small program Jaume Ros and I made at University. It utilizes data from Barcelona Bicing's bike stations and analyzes it using graphs. As an interface between the user and the back-end, a Telegram bot is used.
A method to estimate 3D hand gestures from 3D body motion input in body languages.
No description provided.
No description provided.
This is the project that my team presented at the HackUPC 2021. We implemented a recomender system for university students to pick their stay abroad. Ths sytem picks the university that best fits the student's needs, based on a series of questions (whose order is decided by the algorithm).