no code implementations • 12 Dec 2023 • Utkarsh Mall, Cheng Perng Phoo, Meilin Kelsey Liu, Carl Vondrick, Bharath Hariharan, Kavita Bala
We introduce a method to train vision-language models for remote-sensing images without using any textual annotations.
no code implementations • CVPR 2023 • Utkarsh Mall, Bharath Hariharan, Kavita Bala
While a vast amount of spatio-temporal satellite image data is readily available, most of it remains unlabelled.
1 code implementation • 14 Apr 2022 • Samar Khanna, Bram Wallace, Kavita Bala, Bharath Hariharan
Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions.
no code implementations • 21 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.
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.
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.
Ranked #5 on Surface Normals Estimation on Stanford-ORB
2 code implementations • CVPR 2021 • Jang Hyun Cho, Utkarsh Mall, Kavita Bala, Bharath Hariharan
With our novel learning objective, our framework can learn high-level semantic concepts.
Ranked #3 on Unsupervised Semantic Segmentation on COCO-Stuff-171
no code implementations • 28 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.
no code implementations • 4 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.
1 code implementation • CVPR 2021 • Hubert Lin, Mitchell Van Zuijlen, Sylvia C. Pont, Maarten W. A. Wijntjes, Kavita Bala
First, we investigate the role of paintings as style images for stylization-based data augmentation.
no code implementations • 24 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.
no code implementations • 16 Feb 2020 • Hubert Lin, Paul Upchurch, Kavita Bala
We propose block sub-image annotation as a replacement for full-image annotation.
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.
no code implementations • 20 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.
no code implementations • 28 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.
12 code implementations • 9 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.
Graphics
2 code implementations • 6 Jun 2017 • Kevin Matzen, Kavita Bala, Noah Snavely
Each day billions of photographs are uploaded to photo-sharing services and social media platforms.
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.
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.
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.
no code implementations • 7 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.
no code implementations • CVPR 2016 • Sean Bell, C. Lawrence Zitnick, Kavita Bala, Ross Girshick
In this paper we present the Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest.
Ranked #224 on Object Detection on COCO test-dev
no code implementations • 19 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.
no code implementations • ICCV 2015 • Andreas Veit, Balazs Kovacs, Sean Bell, Julian McAuley, Kavita Bala, Serge Belongie
In this paper, we propose a novel learning framework to help answer these types of questions.
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.
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.
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.