Picture for Shai Bagon

Shai Bagon

DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video

Add code
Mar 21, 2024
Figure 1 for DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video
Figure 2 for DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video
Figure 3 for DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video
Figure 4 for DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video
Viaarxiv icon

Disentangling Structure and Appearance in ViT Feature Space

Add code
Nov 20, 2023
Figure 1 for Disentangling Structure and Appearance in ViT Feature Space
Figure 2 for Disentangling Structure and Appearance in ViT Feature Space
Figure 3 for Disentangling Structure and Appearance in ViT Feature Space
Figure 4 for Disentangling Structure and Appearance in ViT Feature Space
Viaarxiv icon

TokenFlow: Consistent Diffusion Features for Consistent Video Editing

Add code
Jul 23, 2023
Figure 1 for TokenFlow: Consistent Diffusion Features for Consistent Video Editing
Figure 2 for TokenFlow: Consistent Diffusion Features for Consistent Video Editing
Figure 3 for TokenFlow: Consistent Diffusion Features for Consistent Video Editing
Figure 4 for TokenFlow: Consistent Diffusion Features for Consistent Video Editing
Viaarxiv icon

DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering

Add code
Dec 18, 2022
Figure 1 for DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
Figure 2 for DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
Figure 3 for DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
Figure 4 for DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
Viaarxiv icon

Detecting Bone Lesions in X-Ray Under Diverse Acquisition Conditions

Dec 15, 2022
Figure 1 for Detecting Bone Lesions in X-Ray Under Diverse Acquisition Conditions
Figure 2 for Detecting Bone Lesions in X-Ray Under Diverse Acquisition Conditions
Figure 3 for Detecting Bone Lesions in X-Ray Under Diverse Acquisition Conditions
Figure 4 for Detecting Bone Lesions in X-Ray Under Diverse Acquisition Conditions
Viaarxiv icon

Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation

Add code
Nov 22, 2022
Figure 1 for Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
Figure 2 for Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
Figure 3 for Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
Figure 4 for Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
Viaarxiv icon

Combining Internal and External Constraints for Unrolling Shutter in Videos

Jul 24, 2022
Figure 1 for Combining Internal and External Constraints for Unrolling Shutter in Videos
Figure 2 for Combining Internal and External Constraints for Unrolling Shutter in Videos
Figure 3 for Combining Internal and External Constraints for Unrolling Shutter in Videos
Figure 4 for Combining Internal and External Constraints for Unrolling Shutter in Videos
Viaarxiv icon

Diverse Video Generation from a Single Video

May 11, 2022
Figure 1 for Diverse Video Generation from a Single Video
Figure 2 for Diverse Video Generation from a Single Video
Figure 3 for Diverse Video Generation from a Single Video
Figure 4 for Diverse Video Generation from a Single Video
Viaarxiv icon

Splicing ViT Features for Semantic Appearance Transfer

Add code
Jan 02, 2022
Figure 1 for Splicing ViT Features for Semantic Appearance Transfer
Figure 2 for Splicing ViT Features for Semantic Appearance Transfer
Figure 3 for Splicing ViT Features for Semantic Appearance Transfer
Figure 4 for Splicing ViT Features for Semantic Appearance Transfer
Viaarxiv icon

Deep ViT Features as Dense Visual Descriptors

Add code
Dec 10, 2021
Figure 1 for Deep ViT Features as Dense Visual Descriptors
Figure 2 for Deep ViT Features as Dense Visual Descriptors
Figure 3 for Deep ViT Features as Dense Visual Descriptors
Figure 4 for Deep ViT Features as Dense Visual Descriptors
Viaarxiv icon