# GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images

arXiv: https://arxiv.org/abs/2610.11215 · HTML: https://mlsanity.com/paper/2610.11215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 81 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 25 of 25)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [TripoSR: Fast 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/2403.02151/) (2024)
- [MeshLRM: Large Reconstruction Model for High-Quality Meshes](https://mlsanity.com/paper/2404.12385/) (2024)
- [Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias](https://mlsanity.com/paper/2101.07296/) (2021)
- [HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects](https://mlsanity.com/paper/1904.03167/) (2019)
- [GRUtopia: Dream General Robots in a City at Scale](https://mlsanity.com/paper/2407.10943/) (2024)
- [HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions](https://mlsanity.com/paper/2308.01477/) (2023)
- [SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes](https://mlsanity.com/paper/2602.09153/) (2026)
- [TexVerse: A Universe of 3D Objects with High-Resolution Textures](https://mlsanity.com/paper/2508.10868/) (2025)
- [Articraft: An Agentic System for Scalable Articulated 3D Asset Generation](https://mlsanity.com/paper/2605.15187/) (2026)
- [InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts](https://mlsanity.com/paper/2509.10813/) (2025)
- [MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation](https://mlsanity.com/paper/2603.11633/) (2026)
- [T5Gemma 2: Seeing, Reading, and Understanding Longer](https://mlsanity.com/paper/2512.14856/) (2025)
- [SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation](https://mlsanity.com/paper/2606.28276/) (2026)
- [MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation](https://mlsanity.com/paper/2602.11337/) (2026)
- [RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion](https://mlsanity.com/paper/2506.05285/) (2025)
- [RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space](https://mlsanity.com/paper/2604.01479/) (2026)
- [World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible](https://mlsanity.com/paper/2606.13652/) (2026)
- [UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cross-Attention Routing](https://mlsanity.com/paper/2607.24298/) (2026)
- [ROODI: Reconstructing Occluded Objects with Denoising Inpainters](https://mlsanity.com/paper/2503.10256/) (2025)
- [FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity](https://mlsanity.com/paper/2606.19019/) (2026)
- [ASV3D: Adapting Diffusion-Based Single-View 3D Reconstruction with Extra Imagery](https://mlsanity.com/paper/2608.08132/) (2026)

## Abstract (arXiv)

Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations and inferring surfaces hidden by occlusions. We present GATOR, a generative and agentic framework that recovers textured object assets and their scene-relative pose from one or more images. Our local modality mixer couples patch-aligned RGB, target-mask, and pointmap features before cross-view reasoning, preserving scene context while distinguishing the target from its surroundings. Text-guided semantic conditioning complements these spatial cues with category names and object captions through stage-specific adapters for structure, geometry, and appearance generation. The generated asset initializes a multimodal agent, providing instance-specific geometry and pose for targeted structural and texture refinement through an observation-guided edit-render-review loop. Across synthetic objects, cluttered tabletops, and indoor scenes, GATOR achieves strong geometric and appearance fidelity while recovering scene-relative pose from sparse observations. Time-budget comparisons and scene-level simulation further demonstrate the reconstruction efficiency and simulation readiness. Project page: https://research.nvidia.com/labs/lpr/gator/