DensePose Files

A real-time approach for mapping all human pixels of 2D RGB images

This is an exact mirror of the DensePose project, hosted at https://github.com/facebookresearch/DensePose. SourceForge is not affiliated with DensePose. For more information, see the SourceForge Open Source Mirror Directory.

Name	Modified	Size	InfoDownloads / Week
DensePose source code.tar.gz	2021-03-24	10.0 MB	0
DensePose source code.zip	2021-03-24	10.1 MB	1
Totals: 2 Items		20.1 MB	1

Other Useful Business Software

Keep company data safe with Chrome Enterprise

Protect your business with AI policies and data loss prevention in the browser

Make AI work your way with Chrome Enterprise. Block unapproved sites and set custom data controls that align with your company's policies.

Download Chrome

Gen AI apps are built with MongoDB Atlas

The database for AI-powered applications.

MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.

Start Free

Recommended Projects

FrankMocap
FrankMocap is a monocular 3D human capture system that estimates body, hand, and optionally face pose from a single RGB image or video. It regresses parametric human models (e.g., SMPL/SMPL-X) directly, producing temporally stable meshes and joint angles suitable for animation or analytics. The...
Mesh R-CNN
Mesh R-CNN is a 3D reconstruction and object understanding framework developed by Facebook Research that extends Mask R-CNN into the 3D domain. Built on top of Detectron2 and PyTorch3D, Mesh R-CNN enables end-to-end 3D mesh prediction directly from single RGB images. The model learns to detect,...
PIFuHD
PIFuHD (Pixel-Aligned Implicit Function for 3D human reconstruction at high resolution) is a method and codebase to reconstruct high-fidelity 3D human meshes from a single image. It extends prior PIFu work by increasing resolution and detail, enabling fine geometry in cloth folds, hair, and...
VideoPose3D
VideoPose3D is a deep learning framework that reconstructs 3D human poses from 2D keypoint sequences extracted from videos. It builds on top of convolutional and temporal networks that map 2D joint coordinates over time to consistent 3D skeletons, enabling robust motion capture without...
SAM 2
SAM2 is a next-generation version of the Segment Anything Model (SAM), designed to improve performance, generalization, and efficiency in promptable image segmentation tasks. It retains the core promptable interface—accepting points, boxes, or masks—but incorporates architectural and training...

DensePose Files

A real-time approach for mapping all human pixels of 2D RGB images

Get an email when there's a new version of DensePose