EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

• URL: http://arxiv.org/abs/2605.13152v1
• Date: Wed, 13 May 2026 08:17:45 GMT
• Title: EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
• Abstract summary: Ev is an unsupervised 3D instance segmentation system that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds.<n>To address this, Ev integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) An object completion module that reconstructs partial geometries after discovering objects.<n>We conduct extensive experiments on both real-world and synthetic datasets, demonstrating superior 3D object segmentation performance over all baselines while achieving state-of-the-art results.
• Score: 16.459953869241595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods suffer from structural discrepancies when transferring object priors from synthetic datasets (e.g., ShapeNet) to real scans (e.g., ScanNet), particularly due to morphological variations and occlusion artifacts. To address this, EvObj integrates two innovative modules: (1) An object discerning module that dynamically refines object candidates, enabling continuous adaptation of object priors to target domains; and (2) An object completion module that reconstructs partial geometries after discovering objects. We conduct extensive experiments on both real-world and synthetic datasets, demonstrating superior 3D object segmentation performance over all baselines while achieving state-of-the-art results.

Related papers

• FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation [16.814652408859025]
  We present Found, a novel framework featuring a superpoint-based object discovery agent that incrementally merges suitable neighboring geometric superpoints.<n>Our method exhibits strong generalization in zero-shot and long-tail scenarios, underscoring its potential for scalable, label-free 3D object segmentation.
  arXiv  Detail & Related papers  (2026-05-26T15:32:32Z)
• ArtLLM: Generating Articulated Assets via 3D LLM [19.814132638278547]
  ArtLLM is a novel framework for generating high-quality articulated assets directly from complete 3D meshes.<n>At its core is a 3D multimodal large language model trained on a large-scale articulation dataset.<n> Experiments show that ArtLLM significantly outperforms state-of-the-art methods in both part layout accuracy and joint prediction.
  arXiv  Detail & Related papers  (2026-03-01T15:07:46Z)
• Online 3D Scene Reconstruction Using Neural Object Priors [83.14204014687938]
  This paper addresses the problem of reconstructing a scene online at the level of objects given an RGB-D video sequence.<n>We propose a feature grid mechanism to continuously update object-centric neural implicit representations as new object parts are revealed.<n>Our approach outperforms state-of-the-art neural implicit models for this task in terms of reconstruction accuracy and completeness.
  arXiv  Detail & Related papers  (2025-03-24T17:09:36Z)
• 3D Part Segmentation via Geometric Aggregation of 2D Visual Features [57.20161517451834]
  Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios.<n>Recent works have explored vision-language models (VLMs) as a promising alternative, using multi-view rendering and textual prompting to identify object parts.<n>To address these limitations, we propose COPS, a COmprehensive model for Parts that blends semantics extracted from visual concepts and 3D geometry to effectively identify object parts.
  arXiv  Detail & Related papers  (2024-12-05T15:27:58Z)
• OA-DET3D: Embedding Object Awareness as a General Plug-in for Multi-Camera 3D Object Detection [77.43427778037203]
  We introduce OA-DET3D, a plug-in module that improves 3D object detection.<n> OA-DET3D boosts the representation of objects by leveraging object-centric depth information and foreground pseudo points.<n>We conduct extensive experiments on the nuScenes dataset and Argoverse 2 dataset to validate the merits of OA-DET3D.
  arXiv  Detail & Related papers  (2023-01-13T06:02:31Z)
• Learning to Complete Object Shapes for Object-level Mapping in Dynamic Scenes [30.500198859451434]
  We propose a novel object-level mapping system that can simultaneously segment, track, and reconstruct objects in dynamic scenes. It can further predict and complete their full geometries by conditioning on reconstructions from depth inputs and a category-level shape prior. We evaluate its effectiveness by quantitatively and qualitatively testing it in both synthetic and real-world sequences.
  arXiv  Detail & Related papers  (2022-08-09T22:56:33Z)
• Segmenting Moving Objects via an Object-Centric Layered Representation [100.26138772664811]
  We introduce an object-centric segmentation model with a depth-ordered layer representation. We introduce a scalable pipeline for generating synthetic training data with multiple objects. We evaluate the model on standard video segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-07-05T17:59:43Z)
• Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections [14.899075941080541]
  We present an unsupervised approach for discovering articulated motions in a part-segmented 3D shape collection. Our approach is based on a concept we call category closure: any valid articulation of an object's parts should keep the object in the same semantic category. We evaluate our approach by using it to re-discover part motions from the PartNet-Mobility dataset.
  arXiv  Detail & Related papers  (2022-06-17T00:50:36Z)
• Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans [27.377128012679076]
  We propose to leverage large-scale synthetic datasets of 3D shapes annotated with part information to learn Neural Part Priors. We can optimize over the learned part priors in order to fit to real-world scanned 3D scenes at test time. Experiments on the ScanNet dataset demonstrate that NPPs significantly outperforms state of the art in part decomposition and object completion.
  arXiv  Detail & Related papers  (2022-03-17T15:05:44Z)
• Unsupervised Learning of 3D Object Categories from Videos in the Wild [75.09720013151247]
  We focus on learning a model from multiple views of a large collection of object instances. We propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:57:01Z)
• Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image [102.44347847154867]
  We propose a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives. Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives. Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.
  arXiv  Detail & Related papers  (2020-04-02T17:58:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.