Publication

Unsupervised Learning of 3D Object Categories from Videos in the Wild

Conference on Computer Vision and Pattern Recognition (CVPR)


Abstract

Our goal is to learn a deep network that, given a small number of images of an object of a given category, reconstructs it in 3D. While several recent works have obtained analogous results using synthetic data or assuming the availability of 2D primitives such as keypoints, we are interested in working with challenging real data and with no manual annotations. We thus focus on learning a model from multiple views of a large collection of object instances. We contribute with a new large dataset of object centric videos suitable for training and benchmarking this class of models. We show that existing techniques leveraging meshes, voxels, or implicit surfaces, which work well for reconstructing isolated objects, fail on this challenging data. Finally, we propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction while obtaining a detailed implicit representation of the object surface and texture, also compensating for the noise in the initial SfM reconstruction that bootstrapped the learning process. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks and on our novel dataset. Project webpage: https://henzler.github.io/publication/unsupervised_videos/.

Related Publications

All Publications

arxiv - November 1, 2020

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, Davide Testuggine

IEEE WHC - July 6, 2021

Hasti: Haptic and Audio Synthesis for Texture Interactions

Sonny Chan, Chase Tymms, Nicholas Colonnese

The Journal of the Acoustical Society of America - February 4, 2021

Perceptual implications of different Ambisonics-based methods for binaural reverberation

Isaac Engel, Craig Henry, Sebastià V. Amengual Garí, Philip W. Robinson, Lorenzo Picinali

ICML - July 18, 2021

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, Stéphane Deny

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy