Search papers, labs, and topics across Lattice.
This paper introduces a novel feed-forward framework that directly decomposes 3D scenes into instance-structured token groups from unposed multi-view images, allowing for a more intuitive representation of objects. By pairing instance tokens with anchor tokens that capture local geometry and appearance, the method enables efficient reconstruction, segmentation, and manipulation of 3D scenes without the need for 3D annotations. The approach outperforms traditional per-scene optimization baselines in class-agnostic instance segmentation and facilitates instance-level scene editing and open-vocabulary 3D instance retrieval, significantly enhancing usability in 3D applications.
Instance-structured 3D tokenization enables seamless scene editing and retrieval, transforming how we interact with 3D environments.
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.
