Pixel-Talk/PEAR

[SIGGRAPH‘2026] PEAR :Pixel-aligned Expressive humAn mesh Recovery

What it solves

PEAR addresses the challenge of real-time recovery of expressive 3D human meshes from images or video. It provides a unified framework that can predict expressive human mesh (EHM-s) parameters quickly and accurately without sacrificing detail.

How it works

PEAR uses a pixel-aligned approach to recover 3D human meshes. It is designed for high-speed performance, capable of predicting parameters at a rate of 100 FPS, making it suitable for real-time applications. The system integrates with standard human body models such as SMPL, SMPLX, and FLAME to generate the final 3D mesh.

Who it’s for

This project is intended for researchers and developers working in computer vision, 3D human reconstruction, and digital human animation who need a high-performance, real-time solution for expressive mesh recovery.

Highlights

  • Real-time performance: Predicts EHM-s parameters at 100 FPS.
  • Unified framework: A single system for expressive 3D human mesh recovery.
  • Broad model support: Compatible with SMPL, SMPLX, and FLAME models.
  • Comprehensive tooling: Includes both inference and training code.

Related

  • Project
    PozzettiAndrea/ComfyUI-SAM3DBody

    A ComfyUI wrapper for Meta's SAM 3D Body that enables full-body 3D human mesh recovery from a single image.

  • Project
    spear-sim/spear

    A Python library for photorealistic embodied AI research that provides deep programmatic control over Unreal Engine applications with high-speed rendering and extensive API access.

  • Project
    facebookresearch/MHR

    A high-fidelity parametric 3D human body model that uses identity, pose, and facial expression parameters to generate realistic, differentiable human meshes.

  • Project
    phamquiluan/ResidualMaskingNetwork

    A facial expression recognition system using a Residual Masking Network to detect human emotions from images and live video feeds.

  • Dispatch
    BAIR PEVA: Whole-Body Conditioned Egocentric Video Prediction

    BAIR introduces PEVA, a world model for embodied agents that predicts egocentric video frames based on high-dimensional whole-body kinematic pose trajectories.