Search Results for author: Soumyadip Sengupta

Found 18 papers, 9 papers with code

MVPSNet: Fast Generalizable Multi-view Photometric Stereo

no code implementations18 May 2023 Dongxu Zhao, Daniel Lichy, Pierre-Nicolas Perrin, Jan-Michael Frahm, Soumyadip Sengupta

We propose a fast and generalizable solution to Multi-view Photometric Stereo (MVPS), called MVPSNet.

Stereo Matching

Motion Matters: Neural Motion Transfer for Better Camera Physiological Sensing

1 code implementation21 Mar 2023 Akshay Paruchuri, Xin Liu, Yulu Pan, Shwetak Patel, Daniel McDuff, Soumyadip Sengupta

Our findings illustrate the utility of motion transfer as a data augmentation technique for improving the generalization of models for camera-based physiological sensing.

Data Augmentation Photoplethysmography (PPG)

A Surface-normal Based Neural Framework for Colonoscopy Reconstruction

no code implementations13 Mar 2023 Shuxian Wang, Yubo Zhang, Sarah K. McGill, Julian G. Rosenman, Jan-Michael Frahm, Soumyadip Sengupta, Stephen M. Pizer

Reconstructing a 3D surface from colonoscopy video is challenging due to illumination and reflectivity variation in the video frame that can cause defective shape predictions.

Universal Guidance for Diffusion Models

1 code implementation14 Feb 2023 Arpit Bansal, Hong-Min Chu, Avi Schwarzschild, Soumyadip Sengupta, Micah Goldblum, Jonas Geiping, Tom Goldstein

Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining.

Face Recognition object-detection +1

Towards Unified Keyframe Propagation Models

1 code implementation19 May 2022 Patrick Esser, Peter Michael, Soumyadip Sengupta

We evaluate our two-stream approach for inpainting tasks, where experiments show that it improves both the propagation of features within a single frame as required for image inpainting, as well as their propagation from keyframes to target frames.

Image Inpainting Video Editing +1

Fast Light-Weight Near-Field Photometric Stereo

no code implementations CVPR 2022 Daniel Lichy, Soumyadip Sengupta, David W. Jacobs

Existing approaches rely on optimization coupled with a far-field PS network operating on pixels or small patches.

Robust High-Resolution Video Matting with Temporal Guidance

1 code implementation25 Aug 2021 Shanchuan Lin, Linjie Yang, Imran Saleemi, Soumyadip Sengupta

We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance.

Image Matting Video Matting +1

A Light Stage on Every Desk

no code implementations ICCV 2021 Soumyadip Sengupta, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz

Whereas existing light stages require expensive, room-scale spherical capture gantries and exist in only a few labs in the world, we demonstrate how to acquire useful data from a normal TV or desktop monitor.

Shape and Material Capture at Home

1 code implementation CVPR 2021 Daniel Lichy, Jiaye Wu, Soumyadip Sengupta, David W. Jacobs

In this paper, we present a technique for estimating the geometry and reflectance of objects using only a camera, flashlight, and optionally a tripod.

Real-Time High-Resolution Background Matting

2 code implementations CVPR 2021 Shanchuan Lin, Andrey Ryabtsev, Soumyadip Sengupta, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman

We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU.

Image Matting Vocal Bursts Intensity Prediction

Background Matting: The World is Your Green Screen

1 code implementation CVPR 2020 Soumyadip Sengupta, Vivek Jayaram, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman

To bridge the domain gap to real imagery with no labeling, we train another matting network guided by the first network and by a discriminator that judges the quality of composites.

Image Matting

Lifespan Age Transformation Synthesis

2 code implementations ECCV 2020 Roy Or-El, Soumyadip Sengupta, Ohad Fried, Eli Shechtman, Ira Kemelmacher-Shlizerman

Most existing aging methods are limited to changing the texture, overlooking transformations in head shape that occur during the human aging and growth process.

Face Age Editing Human Aging +4

A New Rank Constraint on Multi-view Fundamental Matrices, and its Application to Camera Location Recovery

no code implementations CVPR 2017 Soumyadip Sengupta, Tal Amir, Meirav Galun, Tom Goldstein, David W. Jacobs, Amit Singer, Ronen Basri

We show that in general, with the selection of proper scale factors, a matrix formed by stacking fundamental matrices between pairs of images has rank 6.

Cannot find the paper you are looking for? You can Submit a new open access paper.