• Publications
  • Influence
Fast and flexible convolutional sparse coding
TLDR
The proposed method is the first efficient approach to allow for proper boundary conditions to be imposed and it also supports feature learning from incomplete data as well as general reconstruction problems.
DeepVoxels: Learning Persistent 3D Feature Embeddings
TLDR
This work proposes DeepVoxels, a learned representation that encodes the view-dependent appearance of a 3D scene without having to explicitly model its geometry, based on a Cartesian 3D grid of persistent embedded features that learn to make use of the underlying3D scene structure.
Low-budget transient imaging using photonic mixer devices
TLDR
This paper explores the use of photonic mixer devices (PMD), commonly used in inexpensive time-of-flight cameras, as alternative instrumentation for transient imaging, and obtains a sequence of differently modulated images with a PMD sensor, imposes a model for local light/object interaction, and uses an optimization procedure to infer transient images.
Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather
TLDR
A deep fusion network for robust fusion without a large corpus of labeled training data covering all asymmetric distortions is presented, and a single-shot model that adaptively fuses features, driven by measurement entropy is proposed.
End-to-end optimization of optics and image processing for achromatic extended depth of field and super-resolution imaging
TLDR
A fully-differentiable simulation model is built that maps the true source image to the reconstructed one and jointly optimize the optical parameters and the image processing algorithm parameters so as to minimize the deviation between the true and reconstructed image, over a large set of images.
High-quality computational imaging through simple lenses
TLDR
This article estimates per-channel, spatially varying point spread functions, and performs nonblind deconvolution with a novel cross-channel term that is designed to specifically eliminate color fringing.
CALTag: High Precision Fiducial Markers for Camera Calibration
TLDR
A self-identifying marker pattern is presented for camera calibration, designed to support high-precision, fully-automatic localization of calibration points, as well as identification of individual markers in the presence of significant occlusions, uneven illumination, and observations under extremely acute angles.
Diffuse Mirrors: 3D Reconstruction from Diffuse Indirect Illumination Using Inexpensive Time-of-Flight Sensors
TLDR
This paper forms the reconstruction task as a linear inverse problem on the transient response of a scene, which they acquire using an affordable setup consisting of a modulated light source and a time-of-flight image sensor, and achieves resolutions in the order of a few centimeters for object shape and albedo.
Unrolled Optimization with Deep Priors
TLDR
This paper presents unrolled optimization with deep priors, a principled framework for infusing knowledge of the image formation into deep networks that solve inverse problems in imaging, inspired by classical iterative methods.
Temporal frequency probing for 5D transient analysis of global light transport
TLDR
It is observed that transient light transport is always separable in the temporal frequency domain, which makes it possible to analyze transient transport one temporal frequency at a time by trivially adapting techniques from conventional projector-to-camera transport.
...
1
2
3
4
5
...