Daniel Ritchie Source Confirmed
Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.
Assistant Professor
John Brown University
faculty
Research Areas
Links
Is this your profile? Verify and claim your profile
Biography and Research Information
OverviewAI-generated summary
Daniel Ritchie's research spans an impressive range of topics, from computational geometry to the humanities. At John Brown University, he explores 3D shape modeling and computer graphics, with publications focused on generating high-fidelity shapes from natural language descriptions using AI. Recent work includes "CLIP-Sculptor" (2023) and "ShapeCrafter" (2022), which demonstrate novel approaches to text-conditioned 3D shape generation. Beyond the technical realm, Ritchie also investigates educational applications of AI, as seen in his 2023 publication addressing AI-generated writing, and develops AI tools for parent-child interactive storytelling. Additionally, he maintains an active interest in Irish and British Studies, American Constitutional Law, and topic modeling.
Metrics
- h-index: 12
- Publications: 99
- Citations: 639
Selected Publications
- GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities (2025) DOI
- Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy (2025) DOI
- Improving Unsupervised Visual Program Inference with Code Rewriting Families (2023) DOI
- Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly (2023) DOI
- CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language (2023) DOI
- Neurosymbolic Models for Computer Graphics (2023) DOI
- PLAD: Learning to Infer Shape Programs with Pseudo-Labels and Approximate Distributions (2022) DOI
- The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference (2022) DOI
- Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections (2022) DOI
Collaborators
Researchers in the database who share publications
Similar Researchers
Based on overlapping research topics