# Unsupervised Learning of 3D Object Categories from Videos in the Wild Source: [Unsupervised Learning of 3D Object Categories from Videos in the Wild]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:03:46.301Z Authors: Philipp Henzler, Jeremy Reizenstein, Patrick Labatut, Roman Shapovalov, Tobias Ritschel, Andrea Vedaldi, David Novotny Published: 2021-03-30T17:57:01.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Shape Reconstruction on CO3D seen categories v2](): Shape Reconstruction; CO3D seen categories v2; Abs Error: 2.75. - [Shape Reconstruction on CO3D unseen categories v2](): Shape Reconstruction; CO3D unseen categories v2; Abs Error: 2.79. ## Original sources and implementation [Original paper]() [PDF]()