Guénolé Fiche

A new model for human mesh recovery, high-performing and w/o using any 3D scans, has been published by my excellent colleagues at @naverlabseurope.bsky.social. Excellent work!

Meet Anny, our Free (Apache 2.0) and Interpretable Human Body Model for all ages.
Anny is built upon #MakeHuman and enables achieving SOTA performance in Human Mesh Recovery.
ArXiv: arxiv.org/abs/2511.03589
Demo: anny-demo.europe.naverlabs.com
Code: github.com/naver/anny

MEGA is the first method that achieves SOTA results in both single and multi-output HMR. Want to try it yourself? Code and demo are available at: g-fiche.github.io/research-pag...

Work done in collaboration with @sleglaive.bsky.social , @xavirema.bsky.social , and Francesc Moreno-Noguer. (6/6)

We propose 2 generation modes:
- In deterministic mode, MEGA predicts all tokens in a single forward pass, ensuring speed and accuracy.
- In stochastic mode we iteratively sample human mesh tokens, enabling MEGA to produce multiple predictions from a single image. (5/6)

Subsequently, we add image conditioning and train MEGA to recover human meshes from image features and partial token sequences. During inference, we begin with a fully masked sequence of tokens and generate a human mesh conditioned on an input image. (4/6)

MEGA is first pre-trained on motion capture data to recover human meshes from partial human mesh token sequences with a variable masking rate. Starting from an empty sequence, we are then able to generate random meshes showing high pose and shape diversity. (3/6)

MEGA is a MaskEd Generative Autoencoder, which relies on a tokenized representation of human meshes. We frame HMR as generating a sequence of tokens corresponding to a human mesh, conditioned on an input image. (2/6)

Reconstructing 3D humans from a single image is highly ambiguous: many 3D poses can explain the same 2D view. Yet, most HMR methods predict a single mesh! 🤯

At #CVPR2025, we present MEGA, a new approach that tackles this challenge. 🧵👇 (1/6)