Alert button
Picture for Greg Shakhnarovich

Greg Shakhnarovich

Alert button

Generative Models: What do they know? Do they know things? Let's find out!

Nov 28, 2023
Xiaodan Du, Nicholas Kolkin, Greg Shakhnarovich, Anand Bhattad

Viaarxiv icon

Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model

Nov 23, 2023
Jiahao Li, Hao Tan, Kai Zhang, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, Sai Bi

Figure 1 for Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
Figure 2 for Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
Figure 3 for Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
Figure 4 for Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
Viaarxiv icon

HyperFields: Towards Zero-Shot Generation of NeRFs from Text

Oct 27, 2023
Sudarshan Babu, Richard Liu, Avery Zhou, Michael Maire, Greg Shakhnarovich, Rana Hanocka

Viaarxiv icon

LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing

Dec 09, 2022
Nam Anh Dinh, Haochen Wang, Greg Shakhnarovich, Rana Hanocka

Figure 1 for LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing
Figure 2 for LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing
Figure 3 for LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing
Figure 4 for LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing
Viaarxiv icon

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

Dec 01, 2022
Haochen Wang, Xiaodan Du, Jiahao Li, Raymond A. Yeh, Greg Shakhnarovich

Figure 1 for Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
Figure 2 for Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
Figure 3 for Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
Figure 4 for Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
Viaarxiv icon

Text-Free Learning of a Natural Language Interface for Pretrained Face Generators

Sep 08, 2022
Xiaodan Du, Raymond A. Yeh, Nicholas Kolkin, Eli Shechtman, Greg Shakhnarovich

Figure 1 for Text-Free Learning of a Natural Language Interface for Pretrained Face Generators
Figure 2 for Text-Free Learning of a Natural Language Interface for Pretrained Face Generators
Figure 3 for Text-Free Learning of a Natural Language Interface for Pretrained Face Generators
Figure 4 for Text-Free Learning of a Natural Language Interface for Pretrained Face Generators
Viaarxiv icon

Depth Field Networks for Generalizable Multi-view Scene Representation

Jul 28, 2022
Vitor Guizilini, Igor Vasiljevic, Jiading Fang, Rares Ambrus, Greg Shakhnarovich, Matthew Walter, Adrien Gaidon

Figure 1 for Depth Field Networks for Generalizable Multi-view Scene Representation
Figure 2 for Depth Field Networks for Generalizable Multi-view Scene Representation
Figure 3 for Depth Field Networks for Generalizable Multi-view Scene Representation
Figure 4 for Depth Field Networks for Generalizable Multi-view Scene Representation
Viaarxiv icon

Open-Domain Sign Language Translation Learned from Online Video

May 25, 2022
Bowen Shi, Diane Brentari, Greg Shakhnarovich, Karen Livescu

Figure 1 for Open-Domain Sign Language Translation Learned from Online Video
Figure 2 for Open-Domain Sign Language Translation Learned from Online Video
Figure 3 for Open-Domain Sign Language Translation Learned from Online Video
Figure 4 for Open-Domain Sign Language Translation Learned from Online Video
Viaarxiv icon

Adapting CLIP For Phrase Localization Without Further Training

Apr 07, 2022
Jiahao Li, Greg Shakhnarovich, Raymond A. Yeh

Figure 1 for Adapting CLIP For Phrase Localization Without Further Training
Figure 2 for Adapting CLIP For Phrase Localization Without Further Training
Figure 3 for Adapting CLIP For Phrase Localization Without Further Training
Figure 4 for Adapting CLIP For Phrase Localization Without Further Training
Viaarxiv icon