# Mind the Shape Gap: A Benchmark and Baseline for Deformation-Aware 6D Pose Estimation of Agricultural Produce

arXiv: https://arxiv.org/abs/2603.27429 · HTML: https://mlsanity.com/paper/2603.27429/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [CosyPose: Consistent multi-view multi-object 6D pose estimation](https://mlsanity.com/paper/2008.08465/) (2020)
- [MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare](https://mlsanity.com/paper/2212.06870/) (2022)
- [GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence](https://mlsanity.com/paper/2311.14155/) (2023)
- [CNOS: A Strong Baseline for CAD-based Novel Object Segmentation](https://mlsanity.com/paper/2307.11067/) (2023)
- [ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization](https://mlsanity.com/paper/2207.13691/) (2022)
- [Any6D: Model-free 6D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2503.18673/) (2025)
- [OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects](https://mlsanity.com/paper/2407.08711/) (2024)
- [Co-op: Correspondence-based Novel Object Pose Estimation](https://mlsanity.com/paper/2503.17731/) (2025)
- [SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations](https://mlsanity.com/paper/2303.10346/) (2023)
- [DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation](https://mlsanity.com/paper/2107.12549/) (2021)
- [Algorithm Design and Integration for a Robotic Apple Harvesting System](https://mlsanity.com/paper/2203.00582/) (2022)
- [RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking](https://mlsanity.com/paper/2506.17119/) (2025)
- [Single-Shot 6DoF Pose and 3D Size Estimation for Robotic Strawberry Harvesting](https://mlsanity.com/paper/2410.03031/) (2024)
- [Mushroom Segmentation and 3D Pose Estimation from Point Clouds using Fully Convolutional Geometric Features and Implicit Pose Encoding](https://mlsanity.com/paper/2404.12144/) (2024)
- [You Only Pose Once: A Minimalist's Detection Transformer for Monocular RGB Category-level 9D Multi-Object Pose Estimation](https://mlsanity.com/paper/2508.14965/) (2025)
- [Enhanced 6D Pose Estimation for Robotic Fruit Picking](https://mlsanity.com/paper/2305.15856/) (2023)
- [Category-Level 6D Object Pose Estimation in Agricultural Settings Using a Lattice-Deformation Framework and Diffusion-Augmented Synthetic Data](https://mlsanity.com/paper/2505.24636/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Simulation to the Real-World: An In-Field 6D Pose Dataset and Baseline for Robotic Strawberry Harvesting](https://mlsanity.com/paper/2606.11381/) (2026)

## Abstract (arXiv)

Accurate 6D pose estimation for robotic harvesting is fundamentally hindered by the biological deformability and high intra-class shape variability of agricultural produce. Instance-level methods fail in this setting, as obtaining exact 3D models for every unique piece of produce is practically infeasible, while category-level approaches that rely on a fixed template suffer significant accuracy degradation when the prior deviates from the true instance geometry. To bridge such lack of robustness to deformation, we introduce PEAR (Pose and dEformation of Agricultural pRoduce), the first benchmark providing joint 6D pose and per-instance 3D deformation ground truth across 8 produce categories, acquired via a robotic manipulator for high annotation accuracy. Using PEAR, we show that state-of-the-art methods suffer up to 6x performance degradation when faced with the inherent geometric deviations of real-world produce. Motivated by this finding, we propose SEED (Simultaneous Estimation of posE and Deformation), a unified RGB-only framework that jointly predicts 6D pose and explicit lattice deformations from a single image across multiple produce categories. Trained entirely on synthetic data with generative texture augmentation applied at the UV level, SEED outperforms MegaPose on 6 out of 8 categories under identical RGB-only conditions, demonstrating that explicit shape modeling is a critical step toward reliable pose estimation in agricultural robotics.