Episode
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views
- Podcast
- Daily Paper Cast
- Published
- Jul 2, 2026
- Duration seconds
- 1435
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/2d8379e9
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/scenes-as-objects-not-primitives-instance-structured-3d-tokenization-from-unposed-views/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/scenes-as-objects-not-primitives-instance-structured-3d-tokenization-from-unposed-views.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 36 | cs.CV, cs.GR Authors: Mijin Yoo, In Cho, Subin Jeon, Jiwoo Lee, Eunbyung Park, Seon Joo Kim Title: Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views Arxiv: http://arxiv.org/abs/2606.29513v1 Abstract: 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.