CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Sun, 28 Sep 2025 05:13:49 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"68d8c40d-6262" expires: Sun, 28 Dec 2025 15:31:11 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: F686:2DDCFF:7BF19C:8AF397:69514AE6 accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 15:21:11 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210082-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766935271.999486,VS0,VE217 vary: Accept-Encoding x-fastly-request-id: 25bd19c9f3b73c951277f7466d61f394776d2d22 content-length: 3233 Dale Decatur

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

Dale Decatur, Thibault Groueix, Wang Yifan, Rana Hanocka, Vladimir Kim, Matheus Gadelha

ICCV, 2025

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

Project Page PDF arXiv Code

iSeg: Interactive 3D Segmentation via Interactive Attention

Itai Lang, Fei Xu, Dale Decatur, Sudarshan Babu, Rana Hanocka

SIGGRAPH Asia, 2024

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

Project Page PDF arXiv Code

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

Dale Decatur, Itai Lang, Kfir Aberman, Rana Hanocka

CVPR, 2024

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

Project Page PDF arXiv Code

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.