# Shape-biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation

arXiv: https://arxiv.org/abs/2402.04878 · HTML: https://mlsanity.com/paper/2402.04878/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 7 Feb 2024.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [CosyPose: Consistent multi-view multi-object 6D pose estimation](https://mlsanity.com/paper/2008.08465/) (2020)
- [BOP: Benchmark for 6D Object Pose Estimation](https://mlsanity.com/paper/1808.08319/) (2018)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects](https://mlsanity.com/paper/1701.05498/) (2017)
- [BOP Challenge 2020 on 6D Object Localization](https://mlsanity.com/paper/2009.07378/) (2020)
- [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://mlsanity.com/paper/2002.12212/) (2020)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects](https://mlsanity.com/paper/1904.03167/) (2019)
- [BlenderProc](https://mlsanity.com/paper/1911.01911/) (2019)
- [BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects](https://mlsanity.com/paper/2302.13075/) (2023)
- [Photorealistic Image Synthesis for Object Instance Detection](https://mlsanity.com/paper/1902.03334/) (2019)
- [Wide-Depth-Range 6D Object Pose Estimation in Space](https://mlsanity.com/paper/2104.00337/) (2021)
- [Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation](https://mlsanity.com/paper/2203.09836/) (2022)
- [Challenges for Monocular 6D Object Pose Estimation in Robotics](https://mlsanity.com/paper/2307.12172/) (2023)
- [PyraPose: Feature Pyramids for Fast and Accurate Object Pose Estimation under Domain Shift](https://mlsanity.com/paper/2010.16117/) (2020)
- [COPE: End-to-end trainable Constant Runtime Object Pose Estimation](https://mlsanity.com/paper/2208.08807/) (2022)
- [6D Pose Estimation for Textureless Objects on RGB Frames using Multi-View Optimization](https://mlsanity.com/paper/2210.11554/) (2022)

## Built on by (most cited first, 2 of 2)

- [What Do Scan-Derived Class Prototypes Add? Disentangling Supervision, Prototype Content and Query Protocol in Recognition over Frozen Foundation Features](https://mlsanity.com/paper/2609.04381/) (2026)
- [SCOPE: Semantic Conditioning for Sim2Real Category-Level Object Pose Estimation in Robotics](https://mlsanity.com/paper/2509.24572/) (2025)

## Abstract (arXiv)

Recent advances in machine learning have greatly benefited object detection and 6D pose estimation. However, textureless and metallic objects still pose a significant challenge due to few visual cues and the texture bias of CNNs. To address his issue, we propose a strategy for inducing a shape bias to CNN training. In particular, by randomizing textures applied to object surfaces during data rendering, we create training data without consistent textural cues. This methodology allows for seamless integration into existing data rendering engines, and results in negligible computational overhead for data rendering and network training. Our findings demonstrate that the shape bias we induce via randomized texturing, improves over existing approaches using style transfer. We evaluate with three detectors and two pose estimators. For the most recent object detector and for pose estimation in general, estimation accuracy improves for textureless and metallic objects. Additionally we show that our approach increases the pose estimation accuracy in the presence of image noise and strong illumination changes. Code and datasets are publicly available at github.com/hoenigpeter/randomized_texturing.