Abhishek Kar

papers

735

total citations

papers (13)

Probing the 3D Awareness of Visual Foundation Models

CVPR 2024arXiv

138

citations

Unsupervised Semantic Correspondence Using Stable Diffusion

NEURIPS 2023arXiv

128

citations

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

NEURIPS 2023arXiv

126

citations

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

NEURIPS 2022arXiv

citations

SLIDE: Single Image 3D Photography With Soft Layering and Depth-Aware Inpainting

ICCV 2021arXiv

citations

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

CVPR 2024arXiv

citations

Accelerating Neural Field Training via Soft Mining

CVPR 2024arXiv

citations

Learned Monocular Depth Priors in Visual-Inertial Initialization

ECCV 2022arXiv

citations

DC2: Dual-Camera Defocus Control by Learning To Refocus

CVPR 2023

citations

Abhishek Kar

papers (13)

Probing the 3D Awareness of Visual Foundation Models

Unsupervised Semantic Correspondence Using Stable Diffusion

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

SLIDE: Single Image 3D Photography With Soft Layering and Depth-Aware Inpainting

NeRFiller: Completing Scenes via Generative 3D Inpainting

LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs

ASIC: Aligning Sparse in-the-wild Image Collections

Unsupervised Keypoints from Pretrained Diffusion Models

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

Accelerating Neural Field Training via Soft Mining

Learned Monocular Depth Priors in Visual-Inertial Initialization

DC2: Dual-Camera Defocus Control by Learning To Refocus

papers (13)

Probing the 3D Awareness of Visual Foundation Models

Unsupervised Semantic Correspondence Using Stable Diffusion

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

SLIDE: Single Image 3D Photography With Soft Layering and Depth-Aware Inpainting

NeRFiller: Completing Scenes via Generative 3D Inpainting

LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs

ASIC: Aligning Sparse in-the-wild Image Collections

Unsupervised Keypoints from Pretrained Diffusion Models

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

Accelerating Neural Field Training via Soft Mining

Learned Monocular Depth Priors in Visual-Inertial Initialization

DC2: Dual-Camera Defocus Control by Learning To Refocus