Picture for Brendan Duke

Brendan Duke

Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers

Add code
Mar 24, 2023
Viaarxiv icon

Exploring Gradient-based Multi-directional Controls in GANs

Add code
Sep 01, 2022
Figure 1 for Exploring Gradient-based Multi-directional Controls in GANs
Figure 2 for Exploring Gradient-based Multi-directional Controls in GANs
Figure 3 for Exploring Gradient-based Multi-directional Controls in GANs
Figure 4 for Exploring Gradient-based Multi-directional Controls in GANs
Viaarxiv icon

Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers

Add code
May 12, 2022
Figure 1 for Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers
Figure 2 for Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers
Figure 3 for Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers
Figure 4 for Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers
Viaarxiv icon

The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation

Add code
Mar 31, 2021
Figure 1 for The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation
Figure 2 for The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation
Figure 3 for The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation
Figure 4 for The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation
Viaarxiv icon

LOHO: Latent Optimization of Hairstyles via Orthogonalization

Add code
Mar 10, 2021
Figure 1 for LOHO: Latent Optimization of Hairstyles via Orthogonalization
Figure 2 for LOHO: Latent Optimization of Hairstyles via Orthogonalization
Figure 3 for LOHO: Latent Optimization of Hairstyles via Orthogonalization
Figure 4 for LOHO: Latent Optimization of Hairstyles via Orthogonalization
Viaarxiv icon

SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation

Add code
Jan 21, 2021
Figure 1 for SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
Figure 2 for SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
Figure 3 for SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
Figure 4 for SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
Viaarxiv icon

Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking

Add code
Jun 11, 2019
Figure 1 for Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking
Figure 2 for Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking
Figure 3 for Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking
Figure 4 for Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking
Viaarxiv icon

Nail Polish Try-On: Realtime Semantic Segmentation of Small Objects for Native and Browser Smartphone AR Applications

Add code
Jun 10, 2019
Figure 1 for Nail Polish Try-On: Realtime Semantic Segmentation of Small Objects for Native and Browser Smartphone AR Applications
Figure 2 for Nail Polish Try-On: Realtime Semantic Segmentation of Small Objects for Native and Browser Smartphone AR Applications
Figure 3 for Nail Polish Try-On: Realtime Semantic Segmentation of Small Objects for Native and Browser Smartphone AR Applications
Viaarxiv icon

Generalized Hadamard-Product Fusion Operators for Visual Question Answering

Add code
Apr 06, 2018
Figure 1 for Generalized Hadamard-Product Fusion Operators for Visual Question Answering
Figure 2 for Generalized Hadamard-Product Fusion Operators for Visual Question Answering
Figure 3 for Generalized Hadamard-Product Fusion Operators for Visual Question Answering
Figure 4 for Generalized Hadamard-Product Fusion Operators for Visual Question Answering
Viaarxiv icon