# Crafting a multi-task CNN for viewpoint estimation

arXiv: https://arxiv.org/abs/1609.03894 · HTML: https://mlsanity.com/paper/1609.03894/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2016.

## Built on by (most cited first, 5 of 5)

- [ODAM: Object Detection, Association, and Mapping using Posed RGB Video](https://mlsanity.com/paper/2108.10165/) (2021)
- [PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning](https://mlsanity.com/paper/2105.05643/) (2021)
- [PressureVision++: Estimating Fingertip Pressure from Diverse RGB Images](https://mlsanity.com/paper/2301.02310/) (2023)
- [Lifting 2D Object Locations to 3D by Discounting LiDAR Outliers across Objects and Views](https://mlsanity.com/paper/2109.07945/) (2021)
- [Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights](https://mlsanity.com/paper/2304.11487/) (2023)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation. However different ways of formulating this problem have been proposed and the competing approaches have been explored with very different design choices. This paper presents a comparison of these approaches in a unified setting as well as a detailed analysis of the key factors that impact performance. Followingly, we present a new joint training method with the detection task and demonstrate its benefit. We also highlight the superiority of classification approaches over regression approaches, quantify the benefits of deeper architectures and extended training data, and demonstrate that synthetic data is beneficial even when using ImageNet training data. By combining all these elements, we demonstrate an improvement of approximately 5% mAVP over previous state-of-the-art results on the Pascal3D+ dataset. In particular for their most challenging 24 view classification task we improve the results from 31.1% to 36.1% mAVP.