3Description: An Intuitive Human-AI Collaborative 3D Modeling Approach

• URL: http://arxiv.org/abs/2506.21845v1
• Date: Fri, 27 Jun 2025 01:33:46 GMT
• Title: 3Description: An Intuitive Human-AI Collaborative 3D Modeling Approach
• Authors: Zhuodi Cai,
• Abstract summary: 3Description aims to address accessibility and usability challenges in traditional 3D modeling.<n>It enables non-professional individuals to co-create 3D models using verbal and gesture descriptions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper presents 3Description, an experimental human-AI collaborative approach for intuitive 3D modeling. 3Description aims to address accessibility and usability challenges in traditional 3D modeling by enabling non-professional individuals to co-create 3D models using verbal and gesture descriptions. Through a combination of qualitative research, product analysis, and user testing, 3Description integrates AI technologies such as Natural Language Processing and Computer Vision, powered by OpenAI and MediaPipe. Recognizing the web has wide cross-platform capabilities, 3Description is web-based, allowing users to describe the desired model and subsequently adjust its components using verbal and gestural inputs. In the era of AI and emerging media, 3Description not only contributes to a more inclusive and user-friendly design process, empowering more people to participate in the construction of the future 3D world, but also strives to increase human engagement in co-creation with AI, thereby avoiding undue surrender to technology and preserving human creativity.

Related papers

• Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey [154.50661618628433]
  3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and digital twins.<n>Recent advances in feed-forward approaches, driven by deep learning, have revolutionized this field by enabling fast and generalizable 3D reconstruction and view synthesis.
  arXiv  Detail & Related papers  (2025-07-19T06:13:25Z)
• Generative AI Framework for 3D Object Generation in Augmented Reality [0.0]
  This thesis integrates state-of-the-art generative AI models for real-time creation of 3D objects in augmented reality (AR) environments.<n>The framework demonstrates applications across industries such as gaming, education, retail, and interior design.<n>A significant contribution is democratizing 3D model creation, making advanced AI tools accessible to a broader audience.
  arXiv  Detail & Related papers  (2025-02-21T17:01:48Z)
• Coral Model Generation from Single Images for Virtual Reality Applications [22.18438294137604]
  This paper introduces a deep-learning framework that generates high-precision 3D coral models from a single image. The project incorporates Explainable AI (XAI) to transform AI-generated models into interactive "artworks"
  arXiv  Detail & Related papers  (2024-09-04T01:54:20Z)
• ChatHuman: Chatting about 3D Humans with Tools [57.29285473727107]
  ChatHuman is a language-driven system that integrates the capabilities of specialized methods into a unified framework.<n>ChatHuman functions as an assistant proficient in utilizing, analyzing, and interacting with tools specific to 3D human tasks.
  arXiv  Detail & Related papers  (2024-05-07T17:59:31Z)
• Choreographing the Digital Canvas: A Machine Learning Approach to Artistic Performance [9.218587190403174]
  This paper introduces the concept of a design tool for artistic performances based on attribute descriptions. The platform integrates a novel machine-learning (ML) model with an interactive interface to generate and visualize artistic movements.
  arXiv  Detail & Related papers  (2024-03-26T01:42:13Z)
• 3D-GPT: Procedural 3D Modeling with Large Language Models [47.72968643115063]
  We introduce 3D-GPT, a framework utilizing large language models(LLMs) for instruction-driven 3D modeling. 3D-GPT positions LLMs as proficient problem solvers, dissecting the procedural 3D modeling tasks into accessible segments and appointing the apt agent for each task. Our empirical investigations confirm that 3D-GPT not only interprets and executes instructions, delivering reliable results but also collaborates effectively with human designers.
  arXiv  Detail & Related papers  (2023-10-19T17:41:48Z)
• Deep3DSketch+: Rapid 3D Modeling from Single Free-hand Sketches [15.426513559370086]
  We introduce a novel end-to-end approach, Deep3DSketch+, which performs 3D modeling using only a single free-hand sketch without inputting multiple sketches or view information. Experiments demonstrated the effectiveness of our approach with the state-of-the-art (SOTA) performance on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2023-09-22T17:12:13Z)
• Digital Modeling for Everyone: Exploring How Novices Approach Voice-Based 3D Modeling [0.0]
  We explore novice mental models in voice-based 3D modeling by conducting a high-fidelity Wizard of Oz study with 22 participants. We conclude with design implications for voice assistants. For example, they have to: deal with vague, incomplete and wrong commands; provide a set of straightforward commands to shape simple and composite objects; and offer different strategies to select 3D objects.
  arXiv  Detail & Related papers  (2023-07-10T11:03:32Z)
• T2TD: Text-3D Generation Model based on Prior Knowledge Guidance [74.32278935880018]
  We propose a novel text-3D generation model (T2TD), which introduces the related shapes or textual information as the prior knowledge to improve the performance of the 3D generation model. Our approach significantly improves 3D model generation quality and outperforms the SOTA methods on the text2shape datasets.
  arXiv  Detail & Related papers  (2023-05-25T06:05:52Z)
• TEMOS: Generating diverse human motions from textual descriptions [53.85978336198444]
  We address the problem of generating diverse 3D human motions from textual descriptions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE) training with human motion data. We show that TEMOS framework can produce both skeleton-based animations as in prior work, as well more expressive SMPL body motions.
  arXiv  Detail & Related papers  (2022-04-25T14:53:06Z)
• 3D Neural Scene Representations for Visuomotor Control [78.79583457239836]
  We learn models for dynamic 3D scenes purely from 2D visual observations. A dynamics model, constructed over the learned representation space, enables visuomotor control for challenging manipulation tasks.
  arXiv  Detail & Related papers  (2021-07-08T17:49:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.