# DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Field

arXiv: https://arxiv.org/abs/2308.02239 · HTML: https://mlsanity.com/paper/2308.02239/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 4 Aug 2023.

## Builds on (most cited first, 30 of 34)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again](https://mlsanity.com/paper/1711.10006/) (2017)
- [BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth](https://mlsanity.com/paper/1703.10896/) (2017)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2007.08454/) (2020)
- [Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2001.09322/) (2020)
- [FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism](https://mlsanity.com/paper/2103.07054/) (2021)
- [Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence](https://mlsanity.com/paper/2011.13650/) (2020)
- [DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency](https://mlsanity.com/paper/2103.06526/) (2021)
- [Self-supervised 6D Object Pose Estimation for Robot Manipulation](https://mlsanity.com/paper/1909.10159/) (2019)
- [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://mlsanity.com/paper/2103.06422/) (2021)
- [GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting](https://mlsanity.com/paper/2203.07918/) (2022)
- [Deep Implicit Templates for 3D Shape Representation](https://mlsanity.com/paper/2011.14565/) (2020)
- [Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation](https://mlsanity.com/paper/1804.03959/) (2018)
- [CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation](https://mlsanity.com/paper/2203.01929/) (2022)
- [Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks](https://mlsanity.com/paper/2108.08755/) (2021)
- [Deep Model-Based 6D Pose Refinement in RGB](https://mlsanity.com/paper/1810.03065/) (2018)
- [SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2106.14193/) (2021)
- [SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation](https://mlsanity.com/paper/2208.06661/) (2022)
- [iCaps: Iterative Category-level Object Pose and Shape Estimation](https://mlsanity.com/paper/2201.00059/) (2021)

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

- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space](https://mlsanity.com/paper/2504.21749/) (2025)
- [SM3: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects](https://mlsanity.com/paper/2401.09133/) (2024)
- [ShapeICP: Iterative Category-level Object Pose and Shape Estimation from Depth](https://mlsanity.com/paper/2408.13147/) (2024)
- [Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching](https://mlsanity.com/paper/2411.15860/) (2024)

## Abstract (arXiv)

Estimating 6D poses and reconstructing 3D shapes of objects in open-world scenes from RGB-depth image pairs is challenging. Many existing methods rely on learning geometric features that correspond to specific templates while disregarding shape variations and pose differences among objects in the same category. As a result, these methods underperform when handling unseen object instances in complex environments. In contrast, other approaches aim to achieve category-level estimation and reconstruction by leveraging normalized geometric structure priors, but the static prior-based reconstruction struggles with substantial intra-class variations. To solve these problems, we propose the DTF-Net, a novel framework for pose estimation and shape reconstruction based on implicit neural fields of object categories. In DTF-Net, we design a deformable template field to represent the general category-wise shape latent features and intra-category geometric deformation features. The field establishes continuous shape correspondences, deforming the category template into arbitrary observed instances to accomplish shape reconstruction. We introduce a pose regression module that shares the deformation features and template codes from the fields to estimate the accurate 6D pose of each object in the scene. We integrate a multi-modal representation extraction module to extract object features and semantic masks, enabling end-to-end inference. Moreover, during training, we implement a shape-invariant training strategy and a viewpoint sampling method to further enhance the model's capability to extract object pose features. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superiority of DTF-Net in both synthetic and real scenes. Furthermore, we show that DTF-Net effectively supports grasping tasks with a real robot arm.