Dale Decatur

I am a PhD student at the University of Chicago's 3DL (threedle) lab studying computer graphics, 3D computer vision, and deep learning. I am advised by Rana Hanocka. Previously, I interned at Adobe Research.

In my spare time, I love to play ultimate frisbee.

News


  • June 2025: Reusing Computation in Text-to-Image Diffusion, a technique for sharing diffusion denoising steps between similar generations, has been accepted to ICCV 2025.
  • Apr 2024: I received a National Science Foundation Graduate Research Fellowship (NSF GRFP).
  • Feb 2024: 3D Paintbrush has been accepted to CVPR 2024.
  • Nov 2023: We present 3D Paintbrush, which produces precise localizations and highly-detailed local textures on meshes.
  • Feb 2023: 3D Highlighter has been accepted to CVPR 2023 as a highlight paper.
  • Dec 2022: We present 3D Highlighter, which localizes regions on 3D shapes via text descriptions.

Research


Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets

Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets

ICCV, 2025

Our hierarchical diffusion shares denoising steps across correlated prompts to enable more efficient generation of image sets with diffusion models.

iSeg: Interactive 3D Segmentation via Interactive Attention

iSeg: Interactive 3D Segmentation via Interactive Attention

SIGGRAPH Asia, 2024

We propose an interactive segmentation technique for 3D shapes that produces fine-grained segmentations based on user clicks.

3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation

3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation

CVPR, 2024

Our approach generates precise localizations and highly detailed local textures on meshes using text guidance.

3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions

3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions

Dale Decatur, Itai Lang, Rana Hanocka
CVPR, 2023 Highlight Paper

Our technique reasons about where to place seemingly unrelated concepts in semantically meaningful locations on the 3D shape, such as a 'poncho' on a horse or 'shoes' on an alien.

VizExtract: Automatic Relation Extraction from Data Visualizations

VizExtract: Automatic Relation Extraction from Data Visualizations

Dale Decatur, Sanjay Krishnan
ArXiv, 2021

We present a system which extracts and classifies relations between variables from images of plots.

Service


Reviewer
CVPR: 2024, 2025
SIGGRAPH: 2024, 2025
SIGGRAPH Asia: 2023, 2024, 2025
NeurIPS: 2023, 2025
ICCV: 2025
ICLR: 2024, 2025, 2026
ECCV: 2024
ICML: 2025
AAAI: 2025
3DV: 2026
Computer Aided Design: 2023
Graphical Models: 2023
Graphics Replicability Stamp Initiative: 2023