no code implementations • 28 Nov 2023 • Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra, Svetlana Lazebnik, D. A. Forsyth, Anand Bhattad
All three classifiers are denied access to image pixels, and look only at derived geometric features.
no code implementations • 27 Apr 2023 • Anand Bhattad, Viraj Shah, Derek Hoiem, D. A. Forsyth
StyleGAN's disentangled style representation enables powerful image editing by manipulating the latent variables, but accurately mapping real-world images to their latent variables (GAN inversion) remains a challenge.
no code implementations • 20 May 2022 • Anand Bhattad, D. A. Forsyth
We propose a novel method, StyLitGAN, for relighting and resurfacing generated images in the absence of labeled data.
no code implementations • 8 Dec 2021 • D. A. Forsyth, Anand Bhattad, Pranav Asthana, Yuanyi Zhong, YuXiong Wang
Novel theory shows that one can use similar scenes to estimate the different lightings that apply to a given scene, with bounded expected error.
no code implementations • 20 Nov 2020 • D. A. Forsyth, Jason J. Rock
The best modern intrinsic image methods learn a map from image to albedo using rendered models and human judgements.
1 code implementation • ICLR 2020 • Anand Bhattad, Min Jin Chong, Kaizhao Liang, Bo Li, D. A. Forsyth
Machine learning models, especially deep neural networks (DNNs), have been shown to be vulnerable against adversarial examples which are carefully crafted samples with a small magnitude of the perturbation.
no code implementations • CVPR 2019 • Aditya Deshpande, Jyoti Aneja, Li-Wei Wang, Alexander Schwing, D. A. Forsyth
We achieve the trifecta: (1) High accuracy for the diverse captions as evaluated by standard captioning metrics and user studies; (2) Faster computation of diverse captions compared to beam search and diverse beam search; and (3) High diversity as evaluated by counting novel sentences, distinct n-grams and mutual overlap (i. e., mBleu-4) scores.
no code implementations • 31 Mar 2018 • Mao-Chuang Yeh, Shuai Tang, Anand Bhattad, D. A. Forsyth
Style transfer methods produce a transferred image which is a rendering of a content image in the manner of a style image.