Search Results for author: Kavita Bala

Found 27 papers, 10 papers with code

AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning

no code implementations21 Sep 2021 Hadi AlZayer, Hubert Lin, Kavita Bala

To our knowledge, this is the first system that can automatically explore an environment to capture an aesthetic photo with respect to a learned aesthetic estimator.

reinforcement-learning Reinforcement Learning (RL)

Field-Guide-Inspired Zero-Shot Learning

1 code implementation ICCV 2021 Utkarsh Mall, Bharath Hariharan, Kavita Bala

Annotating the full set of attributes for a novel category proves to be a tedious and expensive task in deployment.

Attribute Zero-Shot Learning

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting

no code implementations CVPR 2021 Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, Noah Snavely

We present PhySG, an end-to-end inverse rendering pipeline that includes a fully differentiable renderer and can reconstruct geometry, materials, and illumination from scratch from a set of RGB input images.

Depth Prediction Image Relighting +3

Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Rendering

no code implementations28 Mar 2021 Fujun Luan, Shuang Zhao, Kavita Bala, Zhao Dong

Reconstructing the shape and appearance of real-world objects using measured 2D images has been a long-standing problem in computer vision.

Discovering Underground Maps from Fashion

no code implementations4 Dec 2020 Utkarsh Mall, Kavita Bala, Tamara Berg, Kristen Grauman

The fashion sense -- meaning the clothing styles people wear -- in a geographical region can reveal information about that region.

Insights From A Large-Scale Database of Material Depictions In Paintings

no code implementations24 Nov 2020 Hubert Lin, Mitchell Van Zuijlen, Maarten W. A. Wijntjes, Sylvia C. Pont, Kavita Bala

We also find that FasterRCNN, a model which has been designed for object recognition in natural scenes, can be quickly repurposed for detection of materials in paintings.

Domain Adaptation Interactive Segmentation +1

GeoStyle: Discovering Fashion Trends and Events

1 code implementation ICCV 2019 Utkarsh Mall, Kevin Matzen, Bharath Hariharan, Noah Snavely, Kavita Bala

Understanding fashion styles and trends is of great potential interest to retailers and consumers alike.

Learning Material-Aware Local Descriptors for 3D Shapes

no code implementations20 Oct 2018 Hubert Lin, Melinos Averkiou, Evangelos Kalogerakis, Balazs Kovacs, Siddhant Ranade, Vladimir G. Kim, Siddhartha Chaudhuri, Kavita Bala

Unfortunately, only a small fraction of shapes in 3D repositories are labeled with physical mate- rials, posing a challenge for learning methods.

Material Classification Retrieval

Inverse Transport Networks

no code implementations28 Sep 2018 Chengqian Che, Fujun Luan, Shuang Zhao, Kavita Bala, Ioannis Gkioulekas

We introduce inverse transport networks as a learning architecture for inverse rendering problems where, given input image measurements, we seek to infer physical scene parameters such as shape, material, and illumination.

Inverse Rendering

Deep Painterly Harmonization

12 code implementations9 Apr 2018 Fujun Luan, Sylvain Paris, Eli Shechtman, Kavita Bala

Copying an element from a photo and pasting it into a painting is a challenging task.


StreetStyle: Exploring world-wide clothing styles from millions of photos

2 code implementations6 Jun 2017 Kevin Matzen, Kavita Bala, Noah Snavely

Each day billions of photographs are uploaded to photo-sharing services and social media platforms.


Shading Annotations in the Wild

no code implementations CVPR 2017 Balazs Kovacs, Sean Bell, Noah Snavely, Kavita Bala

We demonstrate the value of our data and network in an application to intrinsic images, where we can reduce decomposition artifacts produced by existing algorithms.

Image Relighting Intrinsic Image Decomposition +2

Deep Photo Style Transfer

21 code implementations CVPR 2017 Fujun Luan, Sylvain Paris, Eli Shechtman, Kavita Bala

This paper introduces a deep-learning approach to photographic style transfer that handles a large variety of image content while faithfully transferring the reference style.

Style Transfer

Deep Feature Interpolation for Image Content Changes

2 code implementations CVPR 2017 Paul Upchurch, Jacob Gardner, Geoff Pleiss, Robert Pless, Noah Snavely, Kavita Bala, Kilian Weinberger

We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolution image transformation.

From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators

no code implementations7 Mar 2016 Paul Upchurch, Noah Snavely, Kavita Bala

We propose a new neural network architecture for solving single-image analogies - the generation of an entire set of stylistically similar images from just a single input image.

Deep Manifold Traversal: Changing Labels with Convolutional Features

no code implementations19 Nov 2015 Jacob R. Gardner, Paul Upchurch, Matt J. Kusner, Yixuan Li, Kilian Q. Weinberger, Kavita Bala, John E. Hopcroft

Many tasks in computer vision can be cast as a "label changing" problem, where the goal is to make a semantic change to the appearance of an image or some subject in an image in order to alter the class membership.

On the Appearance of Translucent Edges

no code implementations CVPR 2015 Ioannis Gkioulekas, Bruce Walter, Edward H. Adelson, Kavita Bala, Todd Zickler

We also discuss the existence of shape and material metamers, or combinations of distinct shape or material parameters that generate the same edge profile.

Material Recognition in the Wild with the Materials in Context Database

no code implementations CVPR 2015 Sean Bell, Paul Upchurch, Noah Snavely, Kavita Bala

In this paper, we introduce a new, large-scale, open dataset of materials in the wild, the Materials in Context Database (MINC), and combine this dataset with deep learning to achieve material recognition and segmentation of images in the wild.

Material Recognition Segmentation

Photometric Ambient Occlusion

1 code implementation CVPR 2013 Daniel Hauagge, Scott Wehrwein, Kavita Bala, Noah Snavely

We present a method for computing ambient occlusion (AO) for a stack of images of a scene from a fixed viewpoint.

Cannot find the paper you are looking for? You can Submit a new open access paper.