# What Do Single-view 3D Reconstruction Networks Learn? Source: [What Do Single-view 3D Reconstruction Networks Learn?]() Collection index: [llms.txt]() Data updated: 2025-12-14T17:08:40.282Z Authors: Maxim Tatarchenko, Stephan R. Richter, Ren\\'e Ranftl, Zhuwen Li, Vladlen Koltun, Thomas Brox Published: 2019-05-09T15:07:57.000Z ## Abstract Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by the idea of having an encoder-decoder network that performs non-trivial reasoning about the 3D structure of the output space. In this work, we set up two alternative approaches that perform image classification and retrieval respectively. These simple baselines yield better results than state-of-the-art methods, both qualitatively and quantitatively. We show that encoder-decoder methods are statistically indistinguishable from these baselines, thus indicating that the current state of the art in single-view object reconstruction does not actually perform reconstruction but image classification. We identify aspects of popular experimental procedures that elicit this behavior and discuss ways to improve the current state of research. ## 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. - [3D Teeth Reconstruction on Panoramic Radiographs (test)](): 3D Teeth Reconstruction; Panoramic Radiographs (test); mIoU: 56.4. ## Original sources and implementation [Original paper]() [PDF]()