SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.07415 · ICCV · 2023

Semantify: Simplifying the Control of 3D Morphable Models using CLIP

Ariel Shamir, Omer Gralnik, Guy Gafni

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1: Semantify offers a method to create and edit a 3D parametric model using semantically meaningful descriptors. Semantify is based on a self-supervised method that utilizes the semantic power of CLIP language-vision model to build a mapping between semantic descriptors to 3DMM model coefficients. This can be used in an interactive application defining a slider for each descriptor (a), or to fit a model to an image in a zero shot manner by feeding the image into CLIP and obtaining a vector of semantic scores that can be mapped to shape parameters (b).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2308.07415")
get_code_for_paper("2308.07415")
have("2308.07415")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2308.07415.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2308.07415.svg)](https://syntology.ai/paper/2308.07415)

Connect an agent — have() is free.