List of recent advances for human avatars, including generation, reconstruction, and editing, etc.

The official implementation of the NeurIPS 2024 paper: DoGaussian: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

Official code for ICCV 2023 paper: "TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering".

We propose a framework that accurately derives the 3D tongue shape from single images. A high detailed 3D point cloud of the tongue surface and a full head topology along with the tongue expression can be estimated from the image domain.

Master thesis work on 3d object reconstruction from 2d images with graph convolution network (pixel2mesh adaption).

Demos and results of our method. Code will be available soon...

Multi-scale AANet+ using iterative residuals and warped features for real-time and scalable state-of-the-art stereo matching.

PyTorchGeoNodes is a differentiable module for reconstructing 3D objects from images using interpretable shape programs.

(END-VO) Endoscope Localization and Dense Surgical Scene Reconstruction for Stereo Endoscopy by Unsupervised Optical Flow and Kanade-Lucas-Tomasi Tracking

This repository showcases our project, presenting an innovative approach to 3D Indoor Mapping and Object Segmentation. With a primary focus on robot navigation in complex environments, we introduce a methodology that uses RGB images for mapping and object segmentation by integrating SimpleRecon and Point-Voxel CNN for efficient scene reconstruction

Contains codes for training placercnn for custom images

Educational implementation of NeRF, designed specifically for enthusiasts eager to dive into the world of Neural Radiance Fields (NeRF).

A DIY-box containing 2 Raspberry Pi cameras connected to a Raspberry Pi 3 to capture multiple stereo images and reconstruct a 3d pointcloud.

I present FreeDimentionalAudio A framework that enables novel 3D binaural audio synthesis. This work showcases my new Ray Tracing approach to spatial audio and my love for music.

Prometheus project about 3D reconstruction

Reconstructing 3D geometry from corresponding image points of two images.

Final degree thesis project titled "3D part-based reconstruction for dynamic objects with temporal regularization" @ UPF 2022

Facial Police a perfect platform for the police authorities to identify the suspects or the criminals through CCTV footages. This provides a thorough facial reconstruction of the image and detection through their databases even from the bluriest image available through footage.

Senior project with Austin Theriault and Ryan Hudson

Stereo vision system based in python3 OpenCV & Qt