Finding 3D Scene Analogies with Multimodal Foundation Models

• URL: http://arxiv.org/abs/2510.23184v1
• Date: Mon, 27 Oct 2025 10:23:31 GMT
• Title: Finding 3D Scene Analogies with Multimodal Foundation Models
• Authors: Junho Kim, Young Min Kim,
• Abstract summary: Connecting current observations with prior experiences helps robots adapt and plan in new, unseen 3D environments.<n>Recently, 3D scene analogies have been proposed to connect two 3D scenes, which are smooth maps that align scene regions with common spatial relationships.<n>We propose to use multimodal foundation models for finding 3D scene analogies in a zero-shot, open-vocabulary setting.
• Score: 21.986538846393874
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Connecting current observations with prior experiences helps robots adapt and plan in new, unseen 3D environments. Recently, 3D scene analogies have been proposed to connect two 3D scenes, which are smooth maps that align scene regions with common spatial relationships. These maps enable detailed transfer of trajectories or waypoints, potentially supporting demonstration transfer for imitation learning or task plan transfer across scenes. However, existing methods for the task require additional training and fixed object vocabularies. In this work, we propose to use multimodal foundation models for finding 3D scene analogies in a zero-shot, open-vocabulary setting. Central to our approach is a hybrid neural representation of scenes that consists of a sparse graph based on vision-language model features and a feature field derived from 3D shape foundation models. 3D scene analogies are then found in a coarse-to-fine manner, by first aligning the graph and refining the correspondence with feature fields. Our method can establish accurate correspondences between complex scenes, and we showcase applications in trajectory and waypoint transfer.

Related papers

• Unified Semantic Transformer for 3D Scene Understanding [55.415468022487005]
  We introduce UNITE, a novel feed-forward neural network that unifies a diverse set of 3D semantic tasks within a single model.<n>Our model operates on unseen scenes in a fully end-to-end manner and only takes a few seconds to infer the full 3D semantic geometry.<n>We demonstrate that UNITE achieves state-of-the-art performance on several different semantic tasks and even outperforms task-specific models.
  arXiv  Detail & Related papers  (2025-12-16T12:49:35Z)
• ZING-3D: Zero-shot Incremental 3D Scene Graphs via Vision-Language Models [0.0]
  ZING-3D is a framework that generates a rich semantic representation of a 3D scene in a zero-shot manner.<n>It also enables incremental updates and geometric grounding in 3D space, making it suitable for downstream robotics applications.<n>Our experiments on scenes from the Replica and HM3D dataset show that ZING-3D is effective at capturing spatial and relational knowledge without the need of task-specific training.
  arXiv  Detail & Related papers  (2025-10-24T00:52:33Z)
• Learning 3D Scene Analogies with Neural Contextual Scene Maps [17.545689536966265]
  3D scene analogies are smooth maps between 3D scene regions that align spatial relationships.<n>We propose neural contextual scene maps, which extract descriptor fields summarizing semantic and geometric contexts.<n>Experiments demonstrate the effectiveness of our approach in identifying scene analogies and transferring trajectories in diverse indoor scenes.
  arXiv  Detail & Related papers  (2025-03-20T06:49:33Z)
• Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors [52.63385546943866]
  We present a text-to-scene generation method (namely, Layout2Scene) using additional semantic layout as the prompt to inject precise control of 3D object positions.<n>To fully leverage 2D diffusion priors in geometry and appearance generation, we introduce a semantic-guided geometry diffusion model and a semantic-geometry guided diffusion model.<n>Our method can generate more plausible and realistic scenes as compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-01-05T12:20:13Z)
• PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models [20.379104447051155]
  We present PointSeg, a training-free paradigm that leverages off-the-shelf vision foundation models to address 3D scene perception tasks.<n>PointSeg can segment anything in 3D scene by acquiring accurate 3D prompts to align their corresponding pixels across frames.<n>Our approach significantly surpasses the state-of-the-art specialist training-free model by 14.1$%$, 12.3$%$, and 12.6$%$ mAP on ScanNet, ScanNet++, and KITTI-360 datasets.
  arXiv  Detail & Related papers  (2024-03-11T03:28:20Z)
• Blocks2World: Controlling Realistic Scenes with Editable Primitives [5.541644538483947]
  We present Blocks2World, a novel method for 3D scene rendering and editing. Our technique begins by extracting 3D parallelepipeds from various objects in a given scene using convex decomposition. The next stage involves training a conditioned model that learns to generate images from the 2D-rendered convex primitives.
  arXiv  Detail & Related papers  (2023-07-07T21:38:50Z)
• SGAligner : 3D Scene Alignment with Scene Graphs [84.01002998166145]
  Building 3D scene graphs has emerged as a topic in scene representation for several embodied AI applications. We focus on the fundamental problem of aligning pairs of 3D scene graphs whose overlap can range from zero to partial. We propose SGAligner, the first method for aligning pairs of 3D scene graphs that is robust to in-the-wild scenarios.
  arXiv  Detail & Related papers  (2023-04-28T14:39:22Z)
• OpenScene: 3D Scene Understanding with Open Vocabularies [73.1411930820683]
  Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a model for a single task with supervision. We propose OpenScene, an alternative approach where a model predicts dense features for 3D scene points that are co-embedded with text and image pixels in CLIP feature space. This zero-shot approach enables task-agnostic training and open-vocabulary queries.
  arXiv  Detail & Related papers  (2022-11-28T18:58:36Z)
• Neural Groundplans: Persistent Neural Scene Representations from a Single Image [90.04272671464238]
  We present a method to map 2D image observations of a scene to a persistent 3D scene representation. We propose conditional neural groundplans as persistent and memory-efficient scene representations.
  arXiv  Detail & Related papers  (2022-07-22T17:41:24Z)
• Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions [94.17683799712397]
  We focus on scene graphs, a data structure that organizes the entities of a scene in a graph. We propose a learned method that regresses a scene graph from the point cloud of a scene. We show the application of our method in a domain-agnostic retrieval task, where graphs serve as an intermediate representation for 3D-3D and 2D-3D matching.
  arXiv  Detail & Related papers  (2020-04-08T12:25:25Z)

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.