logo80lv
Articlesclick_arrow
Research
Talentsclick_arrow
Events
Workshops
Aboutclick_arrow
profile_loginLogIn

New Diffusive 3D Human Recovery Approach

Rutgers University unveiled ScoreHMR, a new approach for solving inverse problems for 3D human pose and shape reconstruction, mimicking model fitting techniques, but aligning with the image observation through score guidance in the latent space of a diffusion model.

During CVPR 2024, a group of researchers from Rutgers University presented Score-Guided Human Mesh Recovery (ScoreHMR), a novel approach for solving inverse problems for 3D human pose and shape reconstruction. Like traditional model fitting approaches, ScoreHMR fits a human body model to image observations, yet the alignment with the image observation is achieved through score guidance in the latent space of a diffusion model.

This diffusion model is trained to capture the conditional distribution of the human model parameters given an input image, and by guiding its denoising process with a task-specific score, ScoreHMR solves inverse problems for various applications with no need for retraining the task-agnostic model. According to the developers, ScoreHMR is superior over several benchmarks and settings, including single-frame model fitting, and reconstruction from multiple uncalibrated views and video sequences.

Image Credits: ScoreHMR

This is a comparison of ScoreHMR to an optimization approach (ProHMR-fitting) for temporal model fitting to 2D keypoint detections. ProHMR-fitting has more jitter and can sometimes fail on hard poses or unusual viewpoints.

In the demo below, ScoreHMR and ProHMR-fitting are run on top of ProHMR-regression. ScoreHMR can effectively refine the less accurate ProHMR-regression estimate, and results in more faithful 3D reconstructions than the baselines.

The developers also compared their approach (green) with ProHMR-fitting (blue) and SMPLify (grey). ScoreHMR achieves more faithful reconstructions than the optimization baselines.

Image Credits: ScoreHMR

All papers, code, and models are available here. Check them out and don't forget to join our 80 Level Talent platform and our Telegram channel, follow us on InstagramTwitter, and LinkedIn, where we share breakdowns, the latest news, awesome artworks, and more.

20 Ropes Curve Brushes all contained within one Multi-mesh brush and Low poly meshes.

Join discussion

Comments 1

  • Anonymous user

    This is awesome. I wish I knew how to run the code to test on my own samples. I need a YouTube explainer video lol

    0

    Anonymous user

    ·10 months ago·

You might also like

A Week After "Basically Announcing" Minecraft 2, Notch Basically Cancels It

Instead, he and his team will focus on the previously-announced retro-style roguelike.

Rumor: Possible Release Date for Grand Theft Auto 6 Revealed

A video game store from Uruguay appears to have disclosed the launch date for the gaming industry's most anticipated title.

Breaking: Unity Suddenly Lays Off Numerous Developers With a 5 AM Email

Apparently, the entire Unity Behavior team was cut, alongside many other employees.
  • SciFi Trims V1
    by Jonas Ronnegard

    A set of 256 SF trim brushes for ZBrush, all brushes use 2048x2048 16bit alphas and PSD, Tiff, Jpeg alphas are also included.

  • Lips Detail Alpha Pack
    by Todor Nikolov

    Instead of spending hours working on the lip area, you can get beautiful results within minutes with this pack.

We need your consent

We use cookies on this website to make your browsing experience better. By using the site you agree to our use of cookies.Learn more

×