93 citations · 420 across the 18 of their papers we have counts for
24 papers
Activation Regression for Continuous Domain Generalization with Applications to Crop Classification
Samar Khanna, Bram Wallace, Kavita Bala +1
Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions. In this paper, we model geographic generalisation in medium re…
AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning
Hadi AlZayer, Hubert Lin, Kavita Bala
The process of capturing a well-composed photo is difficult and it takes years of experience to master. We propose a novel pipeline for an autonomous agent to automatically capture…
Field-Guide-Inspired Zero-Shot Learning
Utkarsh Mall, Bharath Hariharan, Kavita Bala
Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become…
PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
Kai Zhang, Fujun Luan, Qianqian Wang +2
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…
PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering
Jang Hyun Cho, Utkarsh Mall, Kavita Bala +1
We present a new framework for semantic segmentation without annotations via clustering. Off-the-shelf clustering methods are limited to curated, single-label, and object-centric i…
Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Rendering
Fujun Luan, Shuang Zhao, Kavita Bala +1
Reconstructing the shape and appearance of real-world objects using measured 2D images has been a long-standing problem in computer vision. In this paper, we introduce a new analys…
Materials In Paintings (MIP): An interdisciplinary dataset for perception, art history, and computer vision
Mitchell J. P. van Zuijlen, Hubert Lin, Kavita Bala +2
A painter is free to modify how components of a natural scene are depicted, which can lead to a perceptually convincing image of the distal world. This signals a major difference b…
Discovering Underground Maps from Fashion
Utkarsh Mall, Kavita Bala, Tamara Berg +1
The fashion sense -- meaning the clothing styles people wear -- in a geographical region can reveal information about that region. For example, it can reflect the kind of activitie…
Insights From A Large-Scale Database of Material Depictions In Paintings
Hubert Lin, Mitchell Van Zuijlen, Maarten W. A. Wijntjes +2
Deep learning has paved the way for strong recognition systems which are often both trained on and applied to natural images. In this paper, we examine the give-and-take relationsh…
DeepSemanticHPPC: Hypothesis-based Planning over Uncertain Semantic Point Clouds
Yutao Han, Hubert Lin, Jacopo Banfi +2
Planning in unstructured environments is challenging -- it relies on sensing, perception, scene reconstruction, and reasoning about various uncertainties. We propose DeepSemanticHP…
Block Annotation: Better Image Annotation for Semantic Segmentation with Sub-Image Decomposition
Hubert Lin, Paul Upchurch, Kavita Bala
Image datasets with high-quality pixel-level annotations are valuable for semantic segmentation: labelling every pixel in an image ensures that rare classes and small objects are a…
GeoStyle: Discovering Fashion Trends and Events
Utkarsh Mall, Kevin Matzen, Bharath Hariharan +2
Understanding fashion styles and trends is of great potential interest to retailers and consumers alike. The photos people upload to social media are a historical and public data s…
Learning Material-Aware Local Descriptors for 3D Shapes
Hubert Lin, Melinos Averkiou, Evangelos Kalogerakis +5
Material understanding is critical for design, geometric modeling, and analysis of functional objects. We enable material-aware 3D shape analysis by employing a projective convolut…
Inverse Transport Networks
Chengqian Che, Fujun Luan, Shuang Zhao +2
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…
Deep Painterly Harmonization
Fujun Luan, Sylvain Paris, Eli Shechtman +1
Copying an element from a photo and pasting it into a painting is a challenging task. Applying photo compositing techniques in this context yields subpar results that look like a c…
StreetStyle: Exploring world-wide clothing styles from millions of photos
Kevin Matzen, Kavita Bala, Noah Snavely
Each day billions of photographs are uploaded to photo-sharing services and social media platforms. These images are packed with information about how people live around the world.…
Shading Annotations in the Wild
Balazs Kovacs, Sean Bell, Noah Snavely +1
Understanding shading effects in images is critical for a variety of vision and graphics problems, including intrinsic image decomposition, shadow removal, image relighting, and in…
Deep Photo Style Transfer
Fujun Luan, Sylvain Paris, Eli Shechtman +1
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. Our a…
Deep Feature Interpolation for Image Content Changes
Paul Upchurch, Jacob Gardner, Geoff Pleiss +4
We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolution image transformation. As the name suggests, it relies only on simple linear in…
From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators
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. So…
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
Sean Bell, C. Lawrence Zitnick, Kavita Bala +1
It is well known that contextual and multi-scale representations are important for accurate visual recognition. In this paper we present the Inside-Outside Net (ION), an object det…
Deep Manifold Traversal: Changing Labels with Convolutional Features
Jacob R. Gardner, Paul Upchurch, Matt J. Kusner +4
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 or…
Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences
Andreas Veit, Balazs Kovacs, Sean Bell +3
With the rapid proliferation of smart mobile devices, users now take millions of photos every day. These include large numbers of clothing and accessory images. We would like to an…
Material Recognition in the Wild with the Materials in Context Database
Sean Bell, Paul Upchurch, Noah Snavely +1
Recognizing materials in real-world images is a challenging task. Real-world materials have rich surface texture, geometry, lighting conditions, and clutter, which combine to make…