# PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views

arXiv: https://arxiv.org/abs/2604.22658 · HTML: https://mlsanity.com/paper/2604.22658/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling](https://mlsanity.com/paper/1804.04610/) (2018)
- [ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding](https://mlsanity.com/paper/2305.08275/) (2023)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding](https://mlsanity.com/paper/2305.10764/) (2023)
- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training](https://mlsanity.com/paper/2308.09718/) (2023)
- [CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition](https://mlsanity.com/paper/2303.11313/) (2023)
- [SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning](https://mlsanity.com/paper/2504.20024/) (2025)
- [Splat-Nav: Safe Real-Time Robot Navigation in Gaussian Splatting Maps](https://mlsanity.com/paper/2403.02751/) (2024)
- [Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions](https://mlsanity.com/paper/2203.17234/) (2022)
- [Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion](https://mlsanity.com/paper/2003.04490/) (2020)
- [Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations](https://mlsanity.com/paper/2510.23607/) (2025)
- [NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation](https://mlsanity.com/paper/2101.12378/) (2021)
- [ImageNet3D: Towards General-Purpose Object-Level 3D Understanding](https://mlsanity.com/paper/2406.09613/) (2024)
- [Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features](https://mlsanity.com/paper/2209.05624/) (2022)
- [A Survey on Deep Geometry Learning: From a Representation Perspective](https://mlsanity.com/paper/2002.07995/) (2020)
- [Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features](https://mlsanity.com/paper/2311.18113/) (2023)
- [Location Field Descriptors: Single Image 3D Model Retrieval in the Wild](https://mlsanity.com/paper/1908.02853/) (2019)
- [RoboTron-Mani: All-in-One Multimodal Large Model for Robotic Manipulation](https://mlsanity.com/paper/2412.07215/) (2024)
- [Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels](https://mlsanity.com/paper/2506.05312/) (2025)
- [Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning](https://mlsanity.com/paper/2010.12238/) (2020)

## Abstract (arXiv)

Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing approaches largely fall into two categories: those using contrastive learning to map point cloud features into existing vision-language spaces and those that learn a common embedding space for 2D images and 3D shapes. However, these feed-forward, holistic alignments are often difficult to interpret, which in turn limits their robustness and generalization to real-world applications. To address this problem, we propose Pose-Aware 3D Shape Retrieval (PASR), a framework that formulates retrieval as a feature-level analysis-by-synthesis problem by distilling knowledge from a 2D foundation model (DINOv3) into a 3D encoder. By aligning pose-conditioned 3D projections with 2D feature maps, our method bridges the gap between real-world images and synthetic meshes. During inference, PASR performs a test-time optimization via analysis-by-synthesis, jointly searching for the shape and pose that best reconstruct the patch-level feature map of the input image. This synthesis-based optimization is inherently robust to partial occlusion and sensitive to fine-grained geometric details. PASR substantially outperforms existing methods on both clean and occluded 3D shape retrieval datasets by a wide margin. Additionally, PASR demonstrates strong multi-task capabilities, achieving robust shape retrieval, competitive pose estimation, and accurate category classification within a single framework.