Aayush Bansal

is this you? claim profile

∙ 0 followers
Carnegie Mellon University

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

Recent neural view synthesis methods have achieved impressive quality an...
04/14/2021 ∙ by Julian Chibane, et al. ∙ 0 ∙ share

read it
Streaming Self-Training via Domain-Agnostic Unlabeled Images

We present streaming self-training (SST) that aims to democratize the pr...
04/07/2021 ∙ by Zhiqiu Lin, et al. ∙ 2 ∙ share

read it
Video Exploration via Video-Specific Autoencoders

We present simple video-specific autoencoders that enables human-control...
03/31/2021 ∙ by Kevin Wang, et al. ∙ 8 ∙ share

read it
Improving task-specific representation via 1M unlabelled images without any extra knowledge

We present a case-study to improve the task-specific representation by l...
06/24/2020 ∙ by Aayush Bansal, et al. ∙ 9 ∙ share

read it
4D Visualization of Dynamic Events from Unconstrained Multi-View Videos

We present a data-driven approach for 4D space-time visualization of dyn...
05/27/2020 ∙ by Aayush Bansal, et al. ∙ 7 ∙ share

read it
Unsupervised Any-to-Many Audiovisual Synthesis via Exemplar Autoencoders

We present an unsupervised approach that enables us to convert the speec...
01/13/2020 ∙ by Kangle Deng, et al. ∙ 6 ∙ share

read it
Shapes and Context: In-the-Wild Image Synthesis & Manipulation

We introduce a data-driven approach for interactively synthesizing in-th...
06/11/2019 ∙ by Aayush Bansal, et al. ∙ 0 ∙ share

read it
Recycle-GAN: Unsupervised Video Retargeting

We introduce a data-driven approach for unsupervised video retargeting t...
08/15/2018 ∙ by Aayush Bansal, et al. ∙ 2 ∙ share

read it
Do Convolutional Neural Networks act as Compositional Nearest Neighbors?

We present a simple approach based on pixel-wise nearest neighbors to un...
11/29/2017 ∙ by Chunhui Liu, et al. ∙ 0 ∙ share

read it
PixelNN: Example-based Image Synthesis

We present a simple nearest-neighbor (NN) approach that synthesizes high...
08/17/2017 ∙ by Aayush Bansal, et al. ∙ 0 ∙ share

read it
Be Careful What You Backpropagate: A Case For Linear Output Activations & Gradient Boosting

In this work, we show that saturating output activation functions, such ...
07/13/2017 ∙ by Anders Oland, et al. ∙ 0 ∙ share

read it
PixelNet: Representation of the pixels, by the pixels, and for the pixels

We explore design principles for general pixel-level prediction problems...
02/21/2017 ∙ by Aayush Bansal, et al. ∙ 0 ∙ share

read it
PixelNet: Towards a General Pixel-level Architecture

We explore architectures for general pixel-level prediction problems, fr...
09/21/2016 ∙ by Aayush Bansal, et al. ∙ 0 ∙ share

read it
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction

We introduce an approach that leverages surface normal predictions, alon...
04/05/2016 ∙ by Aayush Bansal, et al. ∙ 0 ∙ share

read it
Mid-level Elements for Object Detection

Building on the success of recent discriminative mid-level elements, we ...
04/27/2015 ∙ by Aayush Bansal, et al. ∙ 0 ∙ share

read it

Aayush Bansal

Featured Co-authors

Abhinav Gupta

Deva Ramanan

Bhiksha Raj

Gerard Pons-Moll

Abhinav Shrivastava

Xinlei Chen

Yaser Sheikh

Bryan Russell

Carl Doersch

Victor Fragoso

Minh Vo

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

Streaming Self-Training via Domain-Agnostic Unlabeled Images

Video Exploration via Video-Specific Autoencoders

Improving task-specific representation via 1M unlabelled images without any extra knowledge

4D Visualization of Dynamic Events from Unconstrained Multi-View Videos

Unsupervised Any-to-Many Audiovisual Synthesis via Exemplar Autoencoders

Shapes and Context: In-the-Wild Image Synthesis & Manipulation

Recycle-GAN: Unsupervised Video Retargeting

Do Convolutional Neural Networks act as Compositional Nearest Neighbors?

PixelNN: Example-based Image Synthesis

Be Careful What You Backpropagate: A Case For Linear Output Activations & Gradient Boosting

PixelNet: Representation of the pixels, by the pixels, and for the pixels

PixelNet: Towards a General Pixel-level Architecture

Marr Revisited: 2D-3D Alignment via Surface Normal Prediction

Mid-level Elements for Object Detection