41 citations · 85 across the 17 of their papers we have counts for
21 papers
VIN-NBV: A View Introspection Network for Next-Best-View Selection
Noah Frahm, Dongxu Zhao, Andrea Dunn Beltran +4
Next Best View (NBV) algorithms aim to maximize 3D scene acquisition quality using minimal resources, e.g. number of acquisitions, time taken, or distance traversed. Prior methods…
MVPSNet: Fast Generalizable Multi-view Photometric Stereo
Dongxu Zhao, Daniel Lichy, Pierre-Nicolas Perrin +2
We propose a fast and generalizable solution to Multi-view Photometric Stereo (MVPS), called MVPSNet. The key to our approach is a feature extraction network that effectively combi…
A Surface-normal Based Neural Framework for Colonoscopy Reconstruction
Shuxian Wang, Yubo Zhang, Sarah K. McGill +4
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. Aimi…
Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond
Thanh Vu, Baochen Sun, Bodi Yuan +3
The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challe…
A Practical Stereo Depth System for Smart Glasses
Jialiang Wang, Daniel Scharstein, Akash Bapat +11
We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with a fallback…
Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search
Thanh Vu, Yanqi Zhou, Chunfeng Wen +2
In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTas…
Leveraging Disentangled Representations to Improve Vision-Based Keystroke Inference Attacks Under Low Data
John Lim, Jan-Michael Frahm, Fabian Monrose
Keystroke inference attacks are a form of side-channel attacks in which an attacker leverages various techniques to recover a user's keystrokes as she inputs information into some…
VPFusion: Joint 3D Volume and Pixel-Aligned Feature Fusion for Single and Multi-view 3D Reconstruction
Jisan Mahmud, Jan-Michael Frahm
We introduce a unified single and multi-view neural implicit 3D reconstruction framework VPFusion. VPFusion attains high-quality reconstruction using both - 3D feature volume to ca…
ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction
Yubo Zhang, Jan-Michael Frahm, Samuel Ehrenstein +4
One of the key elements of reconstructing a 3D mesh from a monocular video is generating every frame's depth map. However, in the application of colonoscopy video reconstruction, p…
Any-Width Networks
Thanh Vu, Marc Eder, True Price +1
Despite remarkable improvements in speed and accuracy, convolutional neural networks (CNNs) still typically operate as monolithic entities at inference time. This poses a challenge…
Revisiting the Threat Space for Vision-based Keystroke Inference Attacks
John Lim, True Price, Fabian Monrose +1
A vision-based keystroke inference attack is a side-channel attack in which an attacker uses an optical device to record users on their mobile devices and infer their keystrokes. T…
One Shot 3D Photography
Johannes Kopf, Kevin Matzen, Suhib Alsisan +12
3D photography is a new medium that allows viewers to more fully experience a captured moment. In this work, we refer to a 3D photo as one that displays parallax induced by moving…
Reducing Drift in Structure From Motion Using Extended Features
Aleksander Holynski, David Geraghty, Jan-Michael Frahm +2
Low-frequency long-range errors (drift) are an endemic problem in 3D structure from motion, and can often hamper reasonable reconstructions of the scene. In this paper, we present…
Tangent Images for Mitigating Spherical Distortion
Marc Eder, Mykhailo Shvets, John Lim +1
In this work, we propose "tangent images," a spherical image representation that facilitates transferable and scalable computer vision. Inspired by techniques in cartog…
ViewSynth: Learning Local Features from Depth using View Synthesis
Jisan Mahmud, Rajat Vikram Singh, Peri Akiva +3
The rapid development of inexpensive commodity depth sensors has made keypoint detection and matching in the depth image modality an important problem in computer vision. Despite g…
Mapped Convolutions
Marc Eder, True Price, Thanh Vu +2
We present a versatile formulation of the convolution operation that we term a "mapped convolution." The standard convolution operation implicitly samples the pixel grid and comput…
Convolutions on Spherical Images
Marc Eder, Jan-Michael Frahm
Applying convolutional neural networks to spherical images requires particular considerations. We look to the millennia of work on cartographic map projections to provide the tools…
Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
Rui Wang, Stephen M. Pizer, Jan-Michael Frahm
Deep learning-based, single-view depth estimation methods have recently shown highly promising results. However, such methods ignore one of the most important features for determin…
Recurrent Neural Network for Learning DenseDepth and Ego-Motion from Video
Rui Wang, Jan-Michael Frahm, Stephen M. Pizer
Learning-based, single-view depth estimation often generalizes poorly to unseen datasets. While learning-based, two-frame depth estimation solves this problem to some extent by lea…
The Domain Transform Solver
Akash Bapat, Jan-Michael Frahm
We present a framework for edge-aware optimization that is an order of magnitude faster than the state of the art while having comparable performance. Our key insight is that the o…
Self-expressive Dictionary Learning for Dynamic 3D Reconstruction
Enliang Zheng, Dinghuang Ji, Enrique Dunn +1
We target the problem of sparse 3D reconstruction of dynamic objects observed by multiple unsynchronized video cameras with unknown temporal overlap. To this end, we develop a fram…