# Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

arXiv: https://arxiv.org/abs/2606.29513 · HTML: https://mlsanity.com/paper/2606.29513/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 36 references that are in the map.
- First posted on arXiv 28 Jun 2026.

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

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views](https://mlsanity.com/paper/2505.23716/) (2025)
- [Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs](https://mlsanity.com/paper/2408.13912/) (2024)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [Large Spatial Model: End-to-end Unposed Images to Semantic 3D](https://mlsanity.com/paper/2410.18956/) (2024)
- [LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes](https://mlsanity.com/paper/2410.14462/) (2024)
- [IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction](https://mlsanity.com/paper/2510.22706/) (2025)
- [Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images](https://mlsanity.com/paper/2508.03643/) (2025)
- [ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting](https://mlsanity.com/paper/2507.15454/) (2025)
- [Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance Segmentation](https://mlsanity.com/paper/2502.00173/) (2025)
- [C3G: Learning Compact 3D Representations with 2K Gaussians](https://mlsanity.com/paper/2512.04021/) (2025)
- [PanSt3R: Multi-view Consistent Panoptic Segmentation](https://mlsanity.com/paper/2506.21348/) (2025)
- [Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking](https://mlsanity.com/paper/2411.16183/) (2024)

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

- [InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding](https://mlsanity.com/paper/2608.07144/) (2026)

## Abstract (arXiv)

A 3D scene is understood through its objects, not the primitives that compose them. Yet feed-forward reconstruction methods output dense, unstructured sets of points or Gaussians, leaving object-level structure to be recovered after the fact. We propose a feed-forward framework that decomposes a scene into instance-structured 3D token groups directly from unposed multi-view images -- compact object-centric units from which reconstruction, segmentation, and manipulation all follow. Each token group pairs an instance token capturing entity-level identity with anchor tokens that encode local geometry and appearance, which are decoded into a set of 3D Gaussians. This two-level factorization decouples object identity from local appearance, making object instances a native interface of the representation rather than a derived product. The token groups are learned through differentiable rendering with joint reconstruction and segmentation supervision, requiring no 3D annotations. Our feed-forward model surpasses per-scene optimization baselines in class-agnostic instance segmentation while remaining competitive in novel view synthesis. Beyond these metrics, the same token groups directly unlock instance-level scene editing -- removing, translating, or inserting objects by operating on their groups -- as well as efficient open-vocabulary 3D instance retrieval, where retrieval complexity scales with the number of instances rather than primitives.