The reviewed record of science sign in
Pith

arxiv: 2406.07163 · v1 · pith:SCB37L6F · submitted 2024-06-11 · cs.CV

FaceGPT: Self-supervised Learning to Chat about 3D Human Faces

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:SCB37L6Frecord.jsonopen to challenge →

classification cs.CV
keywords facegptfacesfacehumanself-supervisedlearningimagesinputs
0
0 comments X
read the original abstract

We introduce FaceGPT, a self-supervised learning framework for Large Vision-Language Models (VLMs) to reason about 3D human faces from images and text. Typical 3D face reconstruction methods are specialized algorithms that lack semantic reasoning capabilities. FaceGPT overcomes this limitation by embedding the parameters of a 3D morphable face model (3DMM) into the token space of a VLM, enabling the generation of 3D faces from both textual and visual inputs. FaceGPT is trained in a self-supervised manner as a model-based autoencoder from in-the-wild images. In particular, the hidden state of LLM is projected into 3DMM parameters and subsequently rendered as 2D face image to guide the self-supervised learning process via image-based reconstruction. Without relying on expensive 3D annotations of human faces, FaceGPT obtains a detailed understanding about 3D human faces, while preserving the capacity to understand general user instructions. Our experiments demonstrate that FaceGPT not only achieves high-quality 3D face reconstructions but also retains the ability for general-purpose visual instruction following. Furthermore, FaceGPT learns fully self-supervised to generate 3D faces based on complex textual inputs, which opens a new direction in human face analysis.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.