Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
- Sean Bell, C. L. Zitnick, K. Bala, Ross B. Girshick
- Computer ScienceComputer Vision and Pattern Recognition
- 14 December 2015
The Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest, provides strong evidence that context and multi-scale representations improve small object detection.
Intrinsic images in the wild
- Sean Bell, K. Bala, Noah Snavely
- Computer ScienceACM Transactions on Graphics
- 27 July 2014
This paper introduces Intrinsic Images in the Wild, a large-scale, public dataset for evaluating intrinsic image decompositions of indoor scenes, and develops a dense CRF-based intrinsic image algorithm for images in the wild that outperforms a range of state-of-the-art intrinsic image algorithms.
Deep Photo Style Transfer
- Fujun Luan, Sylvain Paris, Eli Shechtman, K. Bala
- Computer ScienceComputer Vision and Pattern Recognition
- 22 March 2017
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 and constrain the transformation from the input to the output to be locally affine in colorspace.
Material recognition in the wild with the Materials in Context Database
- Sean Bell, P. Upchurch, Noah Snavely, K. Bala
- Computer ScienceComputer Vision and Pattern Recognition
- 1 December 2014
A new, large-scale, open dataset of materials in the wild, the Materials in Context Database (MINC), is introduced, and convolutional neural networks are trained for two tasks: classifying materials from patches, and simultaneous material recognition and segmentation in full images.
Learning Visual Clothing Style with Heterogeneous Dyadic Co-Occurrences
- Andreas Veit, Balazs Kovacs, Sean Bell, Julian McAuley, K. Bala, Serge J. Belongie
- Computer ScienceIEEE International Conference on Computer Vision
- 24 September 2015
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 answer questions like…
Lightcuts: a scalable approach to illumination
- B. Walter, Sebastian Fernandez, A. Arbree, K. Bala, Michael Donikian, D. Greenberg
- Computer ScienceInternational Conference on Computer Graphics and…
- 1 July 2005
This work shows how a group of lights can be cheaply approximated while bounding the maximum approximation error, and introduces reconstruction cuts that exploit spatial coherence to accelerate the generation of anti-aliased images with complex illumination.
Learning visual similarity for product design with convolutional neural networks
This paper learns an embedding for visual search in interior design that contains two different domains of product images: products cropped from internet scenes, and products in their iconic form and evaluates the search quantitatively and qualitatively and demonstrates high quality results.
Advanced global illumination
- P. Dutré, P. Bekaert, K. Bala
- Computer Science
- 30 August 2006
If you want to design and implement a global illumination rendering system or need to use and modify an existing system for your specific purpose, this book will give you the tools and the understanding to do so.
Optimistic parallelism requires abstractions
- Milind Kulkarni, K. Pingali, B. Walter, Ganesh Ramanarayanan, K. Bala, L. Chew
- Computer ScienceACM-SIGPLAN Symposium on Programming Language…
- 15 June 2007
It is shown that Delaunay mesh generation and agglomerative clustering can be parallelized in a straight-forward way using the Galois approach, and results suggest that Galois is a practical approach to exploiting data parallelism in irregular programs.
PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering
- Jang Hyun Cho, Utkarsh Mall, K. Bala, B. Hariharan
- Computer ScienceComputer Vision and Pattern Recognition
- 30 March 2021
The method, PiCIE (Pixel-level feature Clustering using Invariance and Equivariance), is the first method capable of segmenting both things and stuff categories without any hyperparameter tuning or task-specific pre-processing.
...
...