# Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images

arXiv: https://arxiv.org/abs/2503.13439 · HTML: https://mlsanity.com/paper/2503.13439/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 89 of its 101 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 30 of 89)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model](https://mlsanity.com/paper/2310.15110/) (2023)
- [3D Shape Generation and Completion through Point-Voxel Diffusion](https://mlsanity.com/paper/2104.03670/) (2021)

## Built on by (most cited first, 30 of 54)

- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space](https://mlsanity.com/paper/2508.19247/) (2025)
- [ShapeR: Robust Conditional 3D Shape Generation from Casual Captures](https://mlsanity.com/paper/2601.11514/) (2026)
- [GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation](https://mlsanity.com/paper/2510.20813/) (2025)
- [R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation](https://mlsanity.com/paper/2506.07826/) (2025)
- [SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model](https://mlsanity.com/paper/2512.10957/) (2025)
- [HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video](https://mlsanity.com/paper/2510.05560/) (2025)
- [Orientation Matters: Making 3D Generative Models Orientation-Aligned](https://mlsanity.com/paper/2506.08640/) (2025)
- [3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework](https://mlsanity.com/paper/2512.17459/) (2025)
- [SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling](https://mlsanity.com/paper/2512.05343/) (2025)
- [Video Perception Models for 3D Scene Synthesis](https://mlsanity.com/paper/2506.20601/) (2025)
- [NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction](https://mlsanity.com/paper/2603.04179/) (2026)
- [GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence](https://mlsanity.com/paper/2511.21945/) (2025)
- [FRIDU: Functional Map Refinement with Guided Image Diffusion](https://mlsanity.com/paper/2506.14322/) (2025)
- [SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation](https://mlsanity.com/paper/2602.23359/) (2026)
- [Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors](https://mlsanity.com/paper/2603.18782/) (2026)
- [Syn4D: A Multiview Synthetic 4D Dataset](https://mlsanity.com/paper/2605.05207/) (2026)
- [PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction](https://mlsanity.com/paper/2605.20290/) (2026)
- [Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration](https://mlsanity.com/paper/2511.22533/) (2025)
- [EGM: Efficient Visual Grounding Language Models](https://mlsanity.com/paper/2601.13633/) (2026)
- [MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE](https://mlsanity.com/paper/2602.08961/) (2026)
- [Axolotl3D: a Unified Framework for Faithful 3D Shape Completion](https://mlsanity.com/paper/2607.20660/) (2026)
- [SynergyAmodal: Deocclude Anything with Text Control](https://mlsanity.com/paper/2504.19506/) (2025)
- [Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image](https://mlsanity.com/paper/2603.05908/) (2026)
- [AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation](https://mlsanity.com/paper/2603.25726/) (2026)
- [Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling](https://mlsanity.com/paper/2608.30821/) (2026)
- [TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image](https://mlsanity.com/paper/2609.04911/) (2026)
- [WorldSculpt: Generating Compositional Worlds from Grounded Videos](https://mlsanity.com/paper/2609.05416/) (2026)
- [NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding](https://mlsanity.com/paper/2509.24441/) (2025)
- [HiGS: Hierarchical Generative Scene Framework for Multi-Step Associative Semantic Spatial Composition](https://mlsanity.com/paper/2510.27148/) (2025)

## Abstract (arXiv)

Most image-based 3D object reconstructors assume that objects are fully visible, ignoring occlusions that commonly occur in real-world scenarios. In this paper, we introduce Amodal3R, a conditional 3D generative model designed to reconstruct 3D objects from partial observations. We start from a "foundation" 3D generative model and extend it to recover plausible 3D geometry and appearance from occluded objects. We introduce a mask-weighted multi-head cross-attention mechanism followed by an occlusion-aware attention layer that explicitly leverages occlusion priors to guide the reconstruction process. We demonstrate that, by training solely on synthetic data, Amodal3R learns to recover full 3D objects even in the presence of occlusions in real scenes. It substantially outperforms existing methods that independently perform 2D amodal completion followed by 3D reconstruction, thereby establishing a new benchmark for occlusion-aware 3D reconstruction.