This repository facilitates the creation of Python wheel files (.whl) from the pytorch3d project to streamline the installation process on Google Colab.

Official PyTorch implementation of BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025). BLADE tackles close-range human mesh recovery where perspective distortion is strongest, and solves for camera pose and focal length in addition to SMPL(-X) parameters.

a Pytorch library for multi-view 3D understanding and generation

Generate complete 3D scenes and environments from text descriptions using neural radiance fields and diffusion models - text-to-3D revolution.

The fastest and most intuitive library to manipulate STL files (stereolithography) for C++ and Python, header-only.

This repo contains a UI that captures 360 deg video of a user and sends it to 2 servers. Model server extracts the 3d reconstruction and measurements of user. Base server saves this data

Gmesh supports differentiable rendering of mixed 3D Gaussians and meshes within a single scene.

3D Model Mesh Deformer implemented using PyTorch3D

Covering 3D computer vision concepts and implementations from state-of-the-art papers and architectures

Used Deep learning , torch3D , open3D libraries

Exploring 3D computer vision and geometry processing with Open3D.

Official Code of ACM MM'24 Paper "Unsupervised Multi-view Pedestrian Detection"

This project shows the basic of 3D vision which involves mesh, point cloud and voxel grid. The first part is about transforming 2D data into 3D.

[ICCV 2023 Oral] Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image

Implementing a PointNet based architecture for classification and segmentation with point clouds. Q1 and Q2 focus on implementing, training and testing models. Q3 asks you to quantitatively analyze model robustness.

Sphere Tracing. Optimizing a Neural SDF. VolSDF. Phong Relighting.

Perform Differentiable Volume Rendering: Ray sampling from cameras, Point sampling along rays. Optimizing a basic implicit volume, Optimizing a Neural Radiance Field.

Exploring the types of losses and decoder functions for regressing to voxels, point clouds, and mesh representations from single view RGB input.

Learning the basics of rendering with PyTorch3D, exploring 3D representations, and practicing constructing simple geometry.

This repository contains my paper reviews, solutions and code submissions for projects completed as part of CMSC848F during Fall 2023. Each project is organized in its own folder, with accompanying documentation and any necessary resources.