Alert button
Picture for Svetlana Lazebnik

Svetlana Lazebnik

Alert button

Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now

Nov 28, 2023
Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra, Svetlana Lazebnik, D. A. Forsyth, Anand Bhattad

Viaarxiv icon

Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images

Nov 27, 2023
Aiyu Cui, Jay Mahajan, Viraj Shah, Preeti Gomathinayagam, Svetlana Lazebnik

Figure 1 for Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images
Figure 2 for Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images
Figure 3 for Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images
Figure 4 for Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images
Viaarxiv icon

ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs

Nov 22, 2023
Viraj Shah, Nataniel Ruiz, Forrester Cole, Erika Lu, Svetlana Lazebnik, Yuanzhen Li, Varun Jampani

Viaarxiv icon

JoIN: Joint GANs Inversion for Intrinsic Image Decomposition

May 18, 2023
Viraj Shah, Svetlana Lazebnik, Julien Philip

Figure 1 for JoIN: Joint GANs Inversion for Intrinsic Image Decomposition
Figure 2 for JoIN: Joint GANs Inversion for Intrinsic Image Decomposition
Figure 3 for JoIN: Joint GANs Inversion for Intrinsic Image Decomposition
Figure 4 for JoIN: Joint GANs Inversion for Intrinsic Image Decomposition
Viaarxiv icon

One-Shot Stylization for Full-Body Human Images

Apr 14, 2023
Aiyu Cui, Svetlana Lazebnik

Figure 1 for One-Shot Stylization for Full-Body Human Images
Figure 2 for One-Shot Stylization for Full-Body Human Images
Figure 3 for One-Shot Stylization for Full-Body Human Images
Figure 4 for One-Shot Stylization for Full-Body Human Images
Viaarxiv icon

Robust Online Video Instance Segmentation with Track Queries

Nov 16, 2022
Zitong Zhan, Daniel McKee, Svetlana Lazebnik

Figure 1 for Robust Online Video Instance Segmentation with Track Queries
Figure 2 for Robust Online Video Instance Segmentation with Track Queries
Figure 3 for Robust Online Video Instance Segmentation with Track Queries
Figure 4 for Robust Online Video Instance Segmentation with Track Queries
Viaarxiv icon

MultiStyleGAN: Multiple One-shot Face Stylizations using a Single GAN

Oct 08, 2022
Viraj Shah, Svetlana Lazebnik

Figure 1 for MultiStyleGAN: Multiple One-shot Face Stylizations using a Single GAN
Figure 2 for MultiStyleGAN: Multiple One-shot Face Stylizations using a Single GAN
Figure 3 for MultiStyleGAN: Multiple One-shot Face Stylizations using a Single GAN
Figure 4 for MultiStyleGAN: Multiple One-shot Face Stylizations using a Single GAN
Viaarxiv icon

Transfer of Representations to Video Label Propagation: Implementation Factors Matter

Mar 10, 2022
Daniel McKee, Zitong Zhan, Bing Shuai, Davide Modolo, Joseph Tighe, Svetlana Lazebnik

Figure 1 for Transfer of Representations to Video Label Propagation: Implementation Factors Matter
Figure 2 for Transfer of Representations to Video Label Propagation: Implementation Factors Matter
Figure 3 for Transfer of Representations to Video Label Propagation: Implementation Factors Matter
Figure 4 for Transfer of Representations to Video Label Propagation: Implementation Factors Matter
Viaarxiv icon

Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents

Oct 12, 2021
Shivansh Patel, Saim Wani, Unnat Jain, Alexander Schwing, Svetlana Lazebnik, Manolis Savva, Angel X. Chang

Figure 1 for Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
Figure 2 for Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
Figure 3 for Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
Figure 4 for Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
Viaarxiv icon

Multi-Object Tracking with Hallucinated and Unlabeled Videos

Aug 19, 2021
Daniel McKee, Bing Shuai, Andrew Berneshawi, Manchen Wang, Davide Modolo, Svetlana Lazebnik, Joseph Tighe

Figure 1 for Multi-Object Tracking with Hallucinated and Unlabeled Videos
Figure 2 for Multi-Object Tracking with Hallucinated and Unlabeled Videos
Figure 3 for Multi-Object Tracking with Hallucinated and Unlabeled Videos
Figure 4 for Multi-Object Tracking with Hallucinated and Unlabeled Videos
Viaarxiv icon