Search Results for author:
Found 37 papers, 5 papers with code
KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filter
To further enhance the performance of the observation MLP, we introduce regularization in the canonical space to facilitate the network's ability to learn warping for different frames.
Multistable Shape from Shading Emerges from Patch Diffusion
We introduce a model that reconstructs a multimodal distribution of shapes from a single shading image, which aligns with the human experience of multistable perception.
Correspondences of the Third Kind: Camera Pose Estimation from Object Reflection
In this paper, we introduce correspondences of the third kind we call reflection correspondences and show that they can help estimate camera pose by just looking at objects without relying on the background.
Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance
In this paper, we introduce the first stochastic inverse rendering method, which recovers the attenuated frequency spectrum of an illumination jointly with the reflectance of an object of known geometry from a single image.
Camera Height Doesn't Change: Unsupervised Training for Metric Monocular Road-Scene Depth Estimation
In this paper, we introduce a novel training method for making any monocular depth network learn absolute scale and estimate metric road-scene depth just from regular training data, i. e., driving videos.
SPIDeRS: Structured Polarization for Invisible Depth and Reflectance Sensing
We introduce structured polarization for invisible depth and reflectance sensing (SPIDeRS), the first depth and reflectance sensing method using patterns of polarized light.
DeepShaRM: Multi-View Shape and Reflectance Map Recovery Under Unknown Lighting
We introduce a novel deep reflectance map estimation network that recovers the camera-view reflectance maps from the surface normals of the current geometry estimate and the input multi-view images.
DeePoint: Visual Pointing Recognition and Direction Estimation
The first is the introduction of a first-of-its-kind large-scale dataset for pointing recognition and direction estimation, which we refer to as the DP Dataset.
Fooling Polarization-based Vision using Locally Controllable Polarizing Projection
If so, is that possible to realize these adversarial attacks in the physical world, without being perceived by human eyes?
TransPoser: Transformer as an Optimizer for Joint Object Shape and Pose Estimation
We propose a novel method for joint estimation of shape and pose of rigid objects from their sequentially observed RGB-D images.
InCrowdFormer: On-Ground Pedestrian World Model From Egocentric Views
We introduce an on-ground Pedestrian World Model, a computational model that can predict how pedestrians move around an observer in the crowd on the ground plane, but from just the egocentric-views of the observer.
NeRFrac: Neural Radiance Fields through Refractive Surface
We introduce NeRFrac to realize neural novel view synthesis of scenes captured through refractive surfaces, typically water surfaces.
Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflection
Our key idea is to model the Fresnel reflection and transmission of the surface microgeometry with a collection of oriented mirror facets, both for body and surface reflections.
ViewBirdiformer: Learning to recover ground-plane crowd trajectories and ego-motion from a single ego-centric view
We introduce a novel learning-based method for view birdification, the task of recovering ground-plane trajectories of pedestrians of a crowd and their observer in the same crowd just from the observed ego-centric video.
nLMVS-Net: Deep Non-Lambertian Multi-View Stereo
Our key idea is to formulate MVS as an end-to-end learnable network, which we refer to as nLMVS-Net, that seamlessly integrates radiometric cues to leverage surface normals as view-independent surface features for learned cost volume construction and filtering.
BlindSpotNet: Seeing Where We Cannot See
Next, we introduce BlindSpotNet (BSN), a simple network that fully leverages this dataset for fully automatic estimation of frame-wise blind spot probability maps for arbitrary driving videos.
Dynamic 3D Gaze From Afar: Deep Gaze Estimation From Temporal Eye-Head-Body Coordination
We introduce a novel method and dataset for 3D gaze estimation of a freely moving person from a distance, typically in surveillance views.
Multimodal Material Segmentation
We use semantic segmentation, as a prior to "guide" this filter selection.
Ranked #7 on
Semantic Segmentation
on UPLight
View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements
We introduce view birdification, the problem of recovering ground-plane movements of people in a crowd from an ego-centric video captured from an observer (e. g., a person or a vehicle) also moving in the crowd.
Shape From Sky: Polarimetric Normal Recovery Under the Sky
That is, we show that the unique polarization pattern encoded in the polarimetric appearance of an object captured under the sky can be decoded to reveal the surface normal at each pixel.
Polarimetric Normal Stereo
Our key idea is to introduce a polarimetric cost volume of distance defined on the polarimetric observations and the polarization state computed from the surface normal.
Differential Viewpoints for Ground Terrain Material Recognition
A key concept is differential angular imaging, where small angular variations in image capture enables angular-gradient features for an enhanced appearance representation that improves recognition.
Video Region Annotation with Sparse Bounding Boxes
Video analysis has been moving towards more detailed interpretation (e. g. segmentation) with encouraging progresses.
Invertible Neural BRDF for Object Inverse Rendering
We introduce a novel neural network-based BRDF model and a Bayesian framework for object inverse rendering, i. e., joint estimation of reflectance and natural illumination from a single image of an object of known geometry.
3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture
In this paper, we introduce 3D-GMNet, a deep neural network for 3D object shape reconstruction from a single image.
Appearance and Shape from Water Reflection
In other words, for the first time, we show that capturing a direct and water-reflected scene in a single exposure forms a self-calibrating HDR catadioptric stereo camera.
Variable Ring Light Imaging: Capturing Transient Subsurface Scattering with An Ordinary Camera
We show that the path length of light captured in each of these observations is naturally lower-bounded by the ring light radius.
Recognizing Material Properties from Images
We refer to such material properties as visual material attributes.
Wetness and Color From a Single Multispectral Image
We derive an analytical spectral appearance model of wet surfaces that expresses the characteristic spectral sharpening due to multiple scattering and absorption in the surface.
Differential Angular Imaging for Material Recognition
We realize this by developing a framework for differential angular imaging, where small angular variations in image capture provide an enhanced appearance representation and significant recognition improvement.
Material Recognition from Local Appearance in Global Context
We achieve this by training a fully-convolutional material recognition network end-to-end with only material category supervision.
Integrating Local Material Recognition with Large-Scale Perceptual Attribute Discovery
In this paper, we introduce a novel material category recognition network architecture to show that perceptual attributes can, in fact, be automatically discovered inside a local material recognition framework.
Radiometric Scene Decomposition: Scene Reflectance, Illumination, and Geometry from RGB-D Images
Recovering the radiometric properties of a scene (i. e., the reflectance, illumination, and geometry) is a long-sought ability of computer vision that can provide invaluable information for a wide range of applications.
Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance
In this work, we address the question of what reflectance can reveal about materials in an efficient manner.
Automatically Discovering Local Visual Material Attributes
We argue that it would be ideal to recognize materials without relying on object cues such as shape.
Reflectance Hashing for Material Recognition
Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionality.
Multiview Shape and Reflectance from Natural Illumination
To this end, we derive a probabilistic geometry estimation method that fully exploits the rich signal embedded in complex appearance.
