1 code implementation • 28 Mar 2022 • Martin Hahner, Christos Sakaridis, Mario Bijelic, Felix Heide, Fisher Yu, Dengxin Dai, Luc van Gool
Due to the difficulty of collecting and annotating training data in this setting, we propose a physically based method to simulate the effect of snowfall on real clear-weather LiDAR point clouds.
Ranked #1 on
3D Object Detection
on Heavy Snowfall
no code implementations • 17 Dec 2021 • Seung-Hwan Baek, Felix Heide
Conventional ToF imaging methods estimate the depth by sending pulses of light into a scene and measuring the ToF of the first-arriving photons directly reflected from a scene surface without any temporal delay.
no code implementations • 16 Dec 2021 • Yuxuan Zhang, Bo Dong, Felix Heide
Various defense methods have proposed image-to-image mapping methods, either including these perturbations in the training process or removing them in a preprocessing denoising step.
1 code implementation • 4 Dec 2021 • Amanpreet Walia, Stefanie Walz, Mario Bijelic, Fahim Mannan, Frank Julca-Aguilar, Michael Langer, Werner Ritter, Felix Heide
Gated cameras hold promise as an alternative to scanning LiDAR sensors with high-resolution 3D depth that is robust to back-scatter in fog, snow, and rain.
no code implementations • 2 Dec 2021 • Julian Ost, Issam Laradji, Alejandro Newell, Yuval Bahat, Felix Heide
We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud.
1 code implementation • 26 Nov 2021 • Ilya Chugunov, Yuxuan Zhang, Zhihao Xia, Xuaner, Zhang, Jiawen Chen, Felix Heide
Modern smartphones can continuously stream multi-megapixel RGB images at 60Hz, synchronized with high-quality 3D pose information and low-resolution LiDAR-driven depth estimates.
no code implementations • 16 Sep 2021 • Seung-Hwan Baek, Ethan Tseng, Andrew Maimone, Nathan Matsuda, Grace Kuo, Qiang Fu, Wolfgang Heidrich, Douglas Lanman, Felix Heide
Holographic displays can generate light fields by dynamically modulating the wavefront of a coherent beam of light using a spatial light modulator, promising rich virtual and augmented reality applications.
no code implementations • CVPR 2021 • Emmanuel Onzon, Fahim Mannan, Felix Heide
In this work, we revisit auto-exposure control as an alternative to HDR sensors.
no code implementations • CVPR 2021 • Nicolas Robidoux, Luis E. Garcia Capel, Dong-eun Seo, Avinash Sharma, Federico Ariza, Felix Heide
Traditionally, hardware ISP settings used by downstream vision modules have been chosen by domain experts.
no code implementations • 25 May 2021 • Seung-Hwan Baek, Felix Heide
This allows us, for the first time, to decompose scene light transport into temporal, spatial, and complete polarimetric dimensions that unveil scene properties hidden to conventional methods.
no code implementations • 25 May 2021 • Seung-Hwan Baek, Noah Walsh, Ilya Chugunov, Zheng Shi, Felix Heide
In this work, we close this gap and propose a computational imaging method for all-optical free-space correlation before photo-conversion that achieves micron-scale depth resolution with robustness to surface reflectance and ambient light with conventional silicon intensity sensors.
1 code implementation • 28 Apr 2021 • Julian Knodt, Joe Bartusek, Seung-Hwan Baek, Felix Heide
Recent neural rendering methods have demonstrated accurate view interpolation by predicting volumetric density and color with a neural network.
1 code implementation • CVPR 2021 • Ilya Chugunov, Seung-Hwan Baek, Qiang Fu, Wolfgang Heidrich, Felix Heide
We introduce Mask-ToF, a method to reduce flying pixels (FP) in time-of-flight (ToF) depth captures.
no code implementations • ICLR 2022 • Roger Girgis, Florian Golemo, Felipe Codevilla, Martin Weiss, Jim Aldon D'Souza, Samira Ebrahimi Kahou, Felix Heide, Christopher Pal
AutoBots can produce either the trajectory of one ego-agent or a distribution over the future trajectories for all agents in the scene.
1 code implementation • CVPR 2021 • Zheng Shi, Ethan Tseng, Mario Bijelic, Werner Ritter, Felix Heide
Most of today's supervised imaging and vision approaches, however, rely on training data collected in the real world that is biased towards good weather conditions, with dense fog, snow, and heavy rain as outliers in these datasets.
no code implementations • CVPR 2021 • Buu Phan, Fahim Mannan, Felix Heide
As a result, optimized patterns can become adversarial for the classifier after being transformed by a certain camera ISP and optic but not for others.
no code implementations • ICCV 2021 • Frank Julca-Aguilar, Jason Taylor, Mario Bijelic, Fahim Mannan, Ethan Tseng, Felix Heide
Today's state-of-the-art methods for 3D object detection are based on lidar, stereo, or monocular cameras.
no code implementations • CVPR 2021 • Seung-Hwan Baek, Felix Heide
Active stereo cameras that recover depth from structured light captures have become a cornerstone sensor modality for 3D scene reconstruction and understanding tasks across application domains.
1 code implementation • CVPR 2021 • Julian Ost, Fahim Mannan, Nils Thuerey, Julian Knodt, Felix Heide
Recent implicit neural rendering methods have demonstrated that it is possible to learn accurate view synthesis for complex scenes by predicting their volumetric density and color supervised solely by a set of RGB images.
1 code implementation • CVPR 2020 • Nicolas Scheiner, Florian Kraus, Fangyin Wei, Buu Phan, Fahim Mannan, Nils Appenrodt, Werner Ritter, Jürgen Dickmann, Klaus Dietmayer, Bernhard Sick, Felix Heide
In this work, we depart from visible-wavelength approaches and demonstrate detection, classification, and tracking of hidden objects in large-scale dynamic environments using Doppler radars that can be manufactured at low-cost in series production.
1 code implementation • 21 Jun 2019 • Tobias Gruber, Mario Bijelic, Felix Heide, Werner Ritter, Klaus Dietmayer
This work introduces an evaluation benchmark for depth estimation and completion using high-resolution depth measurements with angular resolution of up to 25" (arcsecond), akin to a 50 megapixel camera with per-pixel depth available.
1 code implementation • CVPR 2020 • Tejas Borkar, Felix Heide, Lina Karam
Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations.
1 code implementation • SIGGRAPH 2019 2019 • Ethan Tseng, Felix Yu, Yuting Yang, Fahim Mannan, Karl St. Arnaud, Derek Nowrouzezahrai, Jean-François Lalonde, Felix Heide
We present a fully automatic system to optimize the parameters of black-box hardware and software image processing pipelines according to any arbitrary (i. e., application-specific) metric.
1 code implementation • CVPR 2020 • Mario Bijelic, Tobias Gruber, Fahim Mannan, Florian Kraus, Werner Ritter, Klaus Dietmayer, Felix Heide
The fusion of multimodal sensor streams, such as camera, lidar, and radar measurements, plays a critical role in object detection for autonomous vehicles, which base their decision making on these inputs.
2 code implementations • ICCV 2019 • Tobias Gruber, Frank Julca-Aguilar, Mario Bijelic, Werner Ritter, Klaus Dietmayer, Felix Heide
The proposed replacement for scanning lidar systems is real-time, handles back-scatter and provides dense depth at long ranges.
1 code implementation • CVPR 2019 • Vincent Sitzmann, Justus Thies, Felix Heide, Matthias Nießner, Gordon Wetzstein, Michael Zollhöfer
In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis.
no code implementations • CVPR 2019 • Wenzheng Chen, Simon Daneau, Fahim Mannan, Felix Heide
Relying on consumer color image sensors, with high fill factor, high quantum efficiency and low read-out noise, we demonstrate high-fidelity color NLOS imaging for scene configurations tackled before with picosecond time resolution.
no code implementations • 13 Jun 2018 • Ana Serrano, Felix Heide, Diego Gutierrez, Gordon Wetzstein, Belen Masia
Current HDR acquisition techniques are based on either (i) fusing multibracketed, low dynamic range (LDR) images, (ii) modifying existing hardware and capturing different exposures simultaneously with multiple sensors, or (iii) reconstructing a single image with spatially-varying pixel exposures.
no code implementations • CVPR 2018 • Shuochen Su, Felix Heide, Gordon Wetzstein, Wolfgang Heidrich
We present an end-to-end image processing framework for time-of-flight (ToF) cameras.
no code implementations • 20 Nov 2017 • Felix Heide, Matthew O'Toole, Kai Zang, David Lindell, Steven Diamond, Gordon Wetzstein
Imaging objects obscured by occluders is a significant challenge for many applications.
1 code implementation • ICCV 2017 • Biswarup Choudhury, Robin Swanson, Felix Heide, Gordon Wetzstein, Wolfgang Heidrich
Convolutional sparse coding (CSC) is a promising direction for unsupervised learning in computer vision.
no code implementations • CVPR 2017 • Matthew O'Toole, Felix Heide, David B. Lindell, Kai Zang, Steven Diamond, Gordon Wetzstein
Computer vision algorithms build on 2D images or 3D videos that capture dynamic events at the millisecond time scale.
2 code implementations • 22 May 2017 • Steven Diamond, Vincent Sitzmann, Felix Heide, Gordon Wetzstein
A broad class of problems at the core of computational imaging, sensing, and low-level computer vision reduces to the inverse problem of extracting latent images that follow a prior distribution, from measurements taken under a known physical image formation model.
no code implementations • 19 May 2017 • Clara Callenberg, Felix Heide, Gordon Wetzstein, Matthias Hullin
Computational photography encompasses a diversity of imaging techniques, but one of the core operations performed by many of them is to compute image differences.
no code implementations • 27 Mar 2017 • Lei Xiao, Felix Heide, Wolfgang Heidrich, Bernhard Schölkopf, Michael Hirsch
Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency.
1 code implementation • 23 Jan 2017 • Steven Diamond, Vincent Sitzmann, Frank Julca-Aguilar, Stephen Boyd, Gordon Wetzstein, Felix Heide
As such, conventional imaging involves processing the RAW sensor measurements in a sequential pipeline of steps, such as demosaicking, denoising, deblurring, tone-mapping and compression.
no code implementations • CVPR 2016 • Shuochen Su, Felix Heide, Robin Swanson, Jonathan Klein, Clara Callenberg, Matthias Hullin, Wolfgang Heidrich
We propose a material classification method using raw time-of-flight (ToF) measurements.
no code implementations • CVPR 2015 • Lei Xiao, Felix Heide, Matthew O'Toole, Andreas Kolb, Matthias B. Hullin, Kyros Kutulakos, Wolfgang Heidrich
Continuous-wave time-of-flight (ToF) cameras show great promise as low-cost depth image sensors in mobile applications.
no code implementations • CVPR 2015 • Felix Heide, Wolfgang Heidrich, Gordon Wetzstein
Convolutional sparse coding (CSC) has become an increasingly important tool in machine learning and computer vision.
no code implementations • CVPR 2014 • Felix Heide, Lei Xiao, Wolfgang Heidrich, Matthias B. Hullin
The functional difference between a diffuse wall and a mirror is well understood: one scatters back into all directions, and the other one preserves the directionality of reflected light.
no code implementations • CVPR 2013 • James Gregson, Felix Heide, Matthias B. Hullin, Mushfiqur Rouf, Wolfgang Heidrich
We present a novel stochastic framework for non-blind deconvolution based on point samples obtained from random walks.