Dale Decatur

28 posts

Dale Decatur

@DecaturDale

CS PhD student @ Uchicago

Katılım Kasım 2014

112 Takip Edilen86 Takipçiler

Sabitlenmiş Tweet

Dale Decatur@DecaturDale·22 Eki

Excited to share our #ICCV2025 work Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets! Our method generates sets of images using significantly less compute than standard diffusion. 📎ddecatur.github.io/hierarchical-d… 1/

GIF

English

3.9K

Dale Decatur@DecaturDale·4 Haz

Come check out our #CVPR2026 paper matching semantic segmentations between images and 3D shapes!

Itai Lang@ItaiLang

📢 Thrilled to present our work Best Segmentation Buddies 🤝 at #CVPR2026 this week! Best Segmentation Buddies is a zero-shot method that matches semantic parts between images in the wild and untextured 3D shapes, even across completely different domains! 🦉✈️ 1/6

English

110

Dale Decatur retweetledi

Richard Liu@allthatissolids·4 Haz

Very excited to be presenting our highlight paper “Deep Feature Deformation Weights” at #CVPR2026! TLDR: Image features make surprisingly good deformation weights. Our feature distillation is the best in the biz. ExHall A&F 555 Poster Session 4 Website: threedle.github.io/dfd/

English

652

Dale Decatur retweetledi

Richard Liu@allthatissolids·22 Eki

Going to be presenting our oral work WIR3D at @ICCVConference today! Please come check it out! 1:45 pm HST @ Exhibit Hall 3 We will also be #384 at poster session 4 afterwards if you want to chat.

GIF

English

6.8K

Dale Decatur@DecaturDale·22 Eki

This work was completed in collaboration with @thibaultgroueix, @toomanyyifans, @RanaHanocka, Vladimir G. Kim, and Matheus Gadelha. Check out our #ICCV2025 poster #153 today during Poster Session #4 from 2:45-4:45 HST! Paper: arxiv.org/abs/2508.21032 7/

English

Dale Decatur@DecaturDale·22 Eki

While our method can be applied to general purpose image generation, our method achieves the most dramatic savings (saves >75% vs standard diffusion) when examples are structurally similar. Some applications of this are style variation, subject variation, and virtual try-on. 6/

GIF

English

Dale Decatur@DecaturDale·22 Eki

GIF

English

3.9K

Dale Decatur retweetledi

Rana Hanocka@RanaHanocka·15 Haz

Our work “Geometry in Style” will be presented at #CVPR2025 on Sunday at 4pm in ExHall D, poster 219. Drop by and say hi! Our technique is capable of performing expressive text-driven deformations that preserve the input shape identity. 1/

English

9.3K

Dale Decatur retweetledi

Rana Hanocka@RanaHanocka·10 Ara

3DL is recruiting PhD students to start in Fall 2025! A thread👇highlighting some of our recent works, and what we are excited to explore next 🚀 Apply by Dec. 16; more info: cs.uchicago.edu/academics/admi… 1/

English

9.4K

Dale Decatur retweetledi

Rana Hanocka@RanaHanocka·5 Ara

📢 Our work iSeg will be presented at #SIGGRAPHAsia2024 today at 340PM Hall B5 (1) - come say hi! iSeg is a new interactive segmentation technique for 3D shapes, producing fine-grained customized segmentations based on user clicks 👆 Project page: threedle.github.io/iSeg/ 1/

English

102

9.7K

Dale Decatur retweetledi

Rana Hanocka@RanaHanocka·17 Eki

Excited to share MeshUp ⬆️, a framework for deforming a mesh into a blend of various target concepts! MeshUp offers control over the influence of each concept by changing the associated weights. Project page: threedle.github.io/MeshUp/ 🧵1/

English

250

23.3K

Dale Decatur retweetledi

Rana Hanocka@RanaHanocka·31 Tem

Come check out TEDi today from 11:05-11:15 in mile high 4 threedle.github.io/TEDi/ #SIGGRAPH2024

GIF

English

2.3K

Dale Decatur retweetledi

Cohere Labs@Cohere_Labs·1 Tem

Tomorrow tune in with @DecaturDale as he presents "Text-Driven Localization and Local Editing of 3D Shapes" with our community-led Computer Vision group! See you there! 👨‍💻 Learn more: cohere.com/events/c4ai-Da…

Cohere Labs@Cohere_Labs

July 2nd, join our community-led Computer Vision group as they welcome @DecaturDale for a talk on "Text-Driven Localization and Local Editing of 3D Shapes." 😄 Learn more: cohere.com/events/c4ai-Da…

English

1.5K

Dale Decatur@DecaturDale·19 Haz

Come check out our #CVPR2024 poster for 3D Paintbrush 🎨🖌️ on 3D text-driven local editing! Happy to chat more at poster #420 in today’s 10:30 session.

Rana Hanocka@RanaHanocka

Excited to share 🎨🖌️ 3D Paintbrush - a method for generating local stylized textures on meshes using text as input! Our method predicts a localization map & a highly detailed texture map which conforms to it threedle.github.io/3d-paintbrush/ (1/3)

English

2.4K

Dale Decatur@DecaturDale·3 Mar

@_jasonliu_ While this work focused on local edits, you can use our CSD loss to perform global texturing as well (such as giving tiger stripes to the entire object)!

English

Jason Liu@_jason_liu_·1 Mar

@DecaturDale This is very cool Dale! Given a random mesh, could this project give it a tiger stripes texture throughout, like in the first column to the right?

English

Dale Decatur@DecaturDale·29 Şub

Our 3D Paintbrush code is now live: github.com/threedle/3d-pa…. Check out our new Cascaded Score Distillation (CSD) loss! If you are already using SDS, you can swap it for CSD to enable higher resolution supervision from cascaded diffusion models. (1/3)

English

11.9K

Dale Decatur@DecaturDale·29 Şub

The idea behind CSD is to leverage all stages of a cascaded diffusion model for supervision. SDS only uses the base (lowest res) stage of a cascaded diffusion model, while our CSD extends SDS to include the super resolution stages as well. (3/3)

English

271

Dale Decatur@DecaturDale·29 Şub

We use CSD to texture meshes, but we speculate that CSD will work on other representations such as NeRFs, images, and more. We created a simple example that applies CSD to image generation & editing: github.com/threedle/3d-pa…. (2/3)

GIF

English

332

Keşfet

@ICCVConference @thibaultgroueix @toomanyyifans @RanaHanocka @elonmusk @BarackObama @taylorswift13 @cristiano