Search Results - "Efros, Alexei A"

Occlusion-Aware Depth Estimation Using Light-Field Cameras by Ting-Chun Wang, Efros, Alexei A., Ramamoorthi, Ravi

“…Consumer-level and high-end light-field cameras are now widely available. Recent work has demonstrated practical methods for passive depth estimation from…”
Get full text

City Forensics: Using Visual Elements to Predict Non-Visual City Attributes by Arietta, Sean M., Efros, Alexei A., Ramamoorthi, Ravi, Agrawala, Maneesh

“…We present a method for automatically identifying and validating predictive relationships between the visual appearance of a city and its non-visual attributes…”
Get full text

Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency by Tulsiani, Shubham, Zhou, Tinghui, Efros, Alexei A., Malik, Jitendra

“…We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D…”
Get full text

Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models by Aubry, Mathieu, Maturana, Daniel, Efros, Alexei A., Russell, Bryan C., Sivic, Josef

“…This paper poses object category detection in images as a type of 2D-to-3D alignment problem, utilizing the large quantities of 3D CAD models that have been…”
Get full text

Estimating the Natural Illumination Conditions from a Single Outdoor Image by Lalonde, Jean-François, Efros, Alexei A., Narasimhan, Srinivasa G.

“…Given a single outdoor image, we present a method for estimating the likely illumination conditions of the scene. In particular, we compute the probability…”
Get full text

Dataset Distillation by Matching Training Trajectories by Cazenavette, George, Wang, Tongzhou, Torralba, Antonio, Efros, Alexei A., Zhu, Jun-Yan

“…Dataset distillation is the task of synthesizing a small dataset such that a model trained on the synthetic set will match the test accuracy of the model…”
Get full text

Unifying Color and Texture Transfer for Predictive Appearance Manipulation by Okura, Fumio, Vanhoey, Kenneth, Bousseau, Adrien, Efros, Alexei A., Drettakis, George

“…Recent color transfer methods use local information to learn the transformation from a source to an exemplar image, and then transfer this appearance change to…”
Get full text

Learning Correspondence From the Cycle-Consistency of Time by Wang, Xiaolong, Jabri, Allan, Efros, Alexei A.

“…We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free…”
Get full text

Unsupervised Visual Representation Learning by Context Prediction by Doersch, Carl, Gupta, Abhinav, Efros, Alexei A.

“…This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a…”
Get full text

InstructPix2Pix: Learning to Follow Image Editing Instructions by Brooks, Tim, Holynski, Aleksander, Efros, Alexei A.

“…We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model…”
Get full text

CNN-Generated Images Are Surprisingly Easy to Spot... for Now by Wang, Sheng-Yu, Wang, Oliver, Zhang, Richard, Owens, Andrew, Efros, Alexei A.

“…In this work we ask whether it is possible to create a "universal" detector for telling apart real images from these generated by a CNN, regardless of…”
Get full text

Putting Objects in Perspective by Hoiem, Derek, Efros, Alexei A., Hebert, Martial

“…Image understanding requires not only individually estimating elements of the visual world but also capturing the interplay among them. In this paper, we…”
Get full text

Recovering surface layout from an image by HOIEM, Derek, EFROS, Alexei A, HEBERT, Martial

“…Issue Title: Special Issue: Celebrating Kanade's Vision Guest Editors: Katsushi Ikeuchi, Gudrun Klinker, Yuichi Ohta and Richard Szeliski Humans have an…”
Get full text

Depth Estimation with Occlusion Modeling Using Light-Field Cameras by Ting-Chun Wang, Efros, Alexei A., Ramamoorthi, Ravi

“…Light-field cameras have become widely available in both consumer and industrial applications. However, most previous approaches do not model occlusions…”
Get full text

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric by Zhang, Richard, Isola, Phillip, Efros, Alexei A., Shechtman, Eli, Wang, Oliver

“…While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite…”
Get full text

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks by Jun-Yan Zhu, Taesung Park, Isola, Phillip, Efros, Alexei A.

“…Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a…”
Get full text

Multi-view Supervision for Single-View Reconstruction via Differentiable Ray Consistency by Tulsiani, Shubham, Tinghui Zhou, Efros, Alexei A., Malik, Jitendra

“…We study the notion of consistency between a 3D shape and a 2D observation and propose a differentiable formulation which allows computing gradients of the 3D…”
Get full text

Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning by Shen, Xi, Efros, Alexei A., Aubry, Mathieu

“…Our goal in this paper is to discover near duplicate patterns in large collections of artworks. This is harder than standard instance mining due to differences…”
Get full text

Few-shot Image Generation via Cross-domain Correspondence by Ojha, Utkarsh, Li, Yijun, Lu, Jingwan, Efros, Alexei A., Jae Lee, Yong, Shechtman, Eli, Zhang, Richard

“…Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to…”
Get full text

Recovering Occlusion Boundaries from an Image by Hoiem, Derek, Efros, Alexei A., Hebert, Martial

“…Occlusion reasoning is a fundamental problem in computer vision. In this paper, we propose an algorithm to recover the occlusion boundaries and depth ordering…”
Get full text