Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Mijin Yoo, In Cho, Subin Jeon, Jiwoo Lee, Eunbyung Park, Seon Joo Kim• 2026

Related benchmarks

TaskDatasetResultRank
View ReconstructionRE10K 2-view (test)
PSNR22.85
13
Novel View ReconstructionScanNet 8
PSNR22.41
6
Source view feature liftingScanNet 2-view
mIoU66.1
5
Target view feature liftingScanNet 2-view
mIoU65.7
5
Class-agnostic novel-view instance segmentationScanNet 8 context views
AP23.5
4
Novel View ReconstructionScanNet 2-view
PSNR25.28
4
Showing 6 of 6 rows

Other info

Follow for update