SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

• URL: http://arxiv.org/abs/2502.13143v2
• Date: Wed, 24 Sep 2025 00:19:51 GMT
• Title: SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
• Authors: Zekun Qi, Wenyao Zhang, Yufei Ding, Runpei Dong, Xinqiang Yu, Jingwen Li, Lingyun Xu, Baoyu Li, Xialin He, Guofan Fan, Jiazhao Zhang, Jiawei He, Jiayuan Gu, Xin Jin, Kaisheng Ma, Zhizheng Zhang, He Wang, Li Yi,
• Abstract summary: We introduce the concept of semantic orientation, which defines object orientations using natural language.<n>By integrating semantic orientation into VLM agents, our SoFar framework enables 6-DoF spatial reasoning and generates robotic actions.
• Score: 50.060274413294586
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While spatial reasoning has made progress in object localization relationships, it often overlooks object orientation-a key factor in 6-DoF fine-grained manipulation. Traditional pose representations rely on pre-defined frames or templates, limiting generalization and semantic grounding. In this paper, we introduce the concept of semantic orientation, which defines object orientations using natural language in a reference-frame-free manner (e.g., the "plug-in" direction of a USB or the "handle" direction of a cup). To support this, we construct OrienText300K, a large-scale dataset of 3D objects annotated with semantic orientations, and develop PointSO, a general model for zero-shot semantic orientation prediction. By integrating semantic orientation into VLM agents, our SoFar framework enables 6-DoF spatial reasoning and generates robotic actions. Extensive experiments demonstrated the effectiveness and generalization of our SoFar, e.g., zero-shot 48.7% successful rate on Open6DOR and zero-shot 74.9% successful rate on SIMPLER-Env.

Related papers

• Towards 3D Object-Centric Feature Learning for Semantic Scene Completion [18.41627244498394]
  Vision-based 3D Semantic Scene Completion (SSC) has received growing attention due to its potential in autonomous driving.<n>We propose Ocean, an object-centric prediction framework that decomposes the scene into individual object instances.<n>We show that Ocean achieves state-of-the-art performance, with mIoU scores of 17.40 and 20.28, respectively.
  arXiv  Detail & Related papers  (2025-11-17T06:28:26Z)
• Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model [51.02616473941499]
  3D object segmentation with Large Language Models (LLMs) has become a prevailing paradigm due to its broad semantics, task flexibility, and strong generalization.<n>However, this paradigm is hindered by representation misalignment: LLMs process high-level semantic tokens, whereas 3D point clouds convey only dense geometric structures.<n>We present the Point Linguist Model (PLM), a general framework that bridges the representation gap between LLMs and dense 3D point clouds.
  arXiv  Detail & Related papers  (2025-09-09T15:01:28Z)
• Orientation Matters: Making 3D Generative Models Orientation-Aligned [39.941774172257105]
  Existing 3D generative models often produce misaligned results due to inconsistent training data.<n>We introduce the task of orientation-aligned 3D object generation, producing 3D objects with consistent orientations across categories.<n>We fine-tune two representative 3D generative models based on multi-view diffusion and 3D variational autoencoder frameworks to produce intuitively aligned objects.
  arXiv  Detail & Related papers  (2025-06-10T09:54:37Z)
• Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks [17.357441373079382]
  We introduce DORI (Discriminative Orientation Reasoning Intelligence), a benchmark establishing object orientation perception as a primary evaluation target.<n>DORI assesses four dimensions of orientation comprehension: frontal alignment, rotational transformations, relative directional relationships, and canonical orientation understanding.<n>Our evaluation of 15 state-of-the-art vision-language models reveals critical limitations.<n>DORI offers implications for improving robotic control, 3D scene reconstruction, and human-AI interaction in physical environments.
  arXiv  Detail & Related papers  (2025-05-27T18:22:44Z)
• IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments [56.85804719947]
  We present IAAO, a framework that builds an explicit 3D model for intelligent agents to gain understanding of articulated objects in their environment through interaction.<n>We first build hierarchical features and label fields for each object state using 3D Gaussian Splatting (3DGS) by distilling mask features and view-consistent labels from multi-view images.<n>We then perform object- and part-level queries on the 3D Gaussian primitives to identify static and articulated elements, estimating global transformations and local articulation parameters along with affordances.
  arXiv  Detail & Related papers  (2025-04-09T12:36:48Z)
• Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models [79.96917782423219]
  Orient Anything is the first expert and foundational model designed to estimate object orientation in a single image.<n>By developing a pipeline to annotate the front face of 3D objects, we collect 2M images with precise orientation annotations.<n>Our model achieves state-of-the-art orientation estimation accuracy in both rendered and real images.
  arXiv  Detail & Related papers  (2024-12-24T18:58:43Z)
• GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding [53.42728468191711]
  Open-Vocabulary 3D object affordance grounding aims to anticipate action possibilities'' regions on 3D objects with arbitrary instructions.<n>We propose GREAT (GeometRy-intEntion collAboraTive inference) for Open-Vocabulary 3D Object Affordance Grounding.
  arXiv  Detail & Related papers  (2024-11-29T11:23:15Z)
• Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning [7.911608620021529]
  Multimodal large language models (MLLMs) act as essential interfaces, connecting humans with AI technologies in multimodal applications. Current MLLMs face challenges in accurately interpreting object orientation in images due to inconsistent orientation annotations in training data. We propose egocentric instruction tuning, which aligns MLLMs' orientation understanding with the user's perspective.
  arXiv  Detail & Related papers  (2024-11-24T15:07:47Z)
• SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models [15.50826328938879]
  We introduce SURDS, a benchmark designed to evaluate the spatial reasoning capabilities of vision language models (VLMs)<n>Built on the nuScenes dataset, SURDS comprises 41,080 vision-question-answer training instances and 9,250 evaluation samples.<n>We propose a reinforcement learning-based alignment scheme leveraging spatially grounded reward signals.
  arXiv  Detail & Related papers  (2024-11-20T08:14:01Z)
• HACMan++: Spatially-Grounded Motion Primitives for Manipulation [28.411361363637006]
  We introduce spatially-grounded parameterized motion primitives in our method HACMan++. By grounding the primitives on a spatial location in the environment, our method is able to effectively generalize across object shape and pose variations. Our approach significantly outperforms existing methods, particularly in complex scenarios demanding both high-level sequential reasoning and object generalization.
  arXiv  Detail & Related papers  (2024-07-11T15:10:14Z)
• GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane [53.388937705785025]
  3D open-vocabulary scene understanding is crucial for advancing augmented reality and robotic applications. We introduce GOI, a framework that integrates semantic features from 2D vision-language foundation models into 3D Gaussian Splatting (3DGS) Our method treats the feature selection process as a hyperplane division within the feature space, retaining only features that are highly relevant to the query.
  arXiv  Detail & Related papers  (2024-05-27T18:57:18Z)
• MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting [97.52388851329667]
  We introduce Marking Open-world Keypoint Affordances (MOKA) to solve robotic manipulation tasks specified by free-form language instructions. Central to our approach is a compact point-based representation of affordance, which bridges the VLM's predictions on observed images and the robot's actions in the physical world. We evaluate and analyze MOKA's performance on various table-top manipulation tasks including tool use, deformable body manipulation, and object rearrangement.
  arXiv  Detail & Related papers  (2024-03-05T18:08:45Z)
• Object-Centric Instruction Augmentation for Robotic Manipulation [29.491990994901666]
  We introduce the textitObject-Centric Instruction Augmentation (OCI) framework to augment highly semantic and information-dense language instruction with position cues. We utilize a Multi-modal Large Language Model (MLLM) to weave knowledge of object locations into natural language instruction. We demonstrate that robotic manipulator imitation policies trained with our enhanced instructions outperform those relying solely on traditional language instructions.
  arXiv  Detail & Related papers  (2024-01-05T13:54:45Z)
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control [140.48218261864153]
  We study how vision-language models trained on Internet-scale data can be incorporated directly into end-to-end robotic control. Our approach leads to performant robotic policies and enables RT-2 to obtain a range of emergent capabilities from Internet-scale training.
  arXiv  Detail & Related papers  (2023-07-28T21:18:02Z)
• 3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding [58.924180772480504]
  3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description. We propose a relation-aware one-stage framework, named 3D Relative Position-aware Network (3-Net)
  arXiv  Detail & Related papers  (2023-07-25T09:33:25Z)
• VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models [38.503337052122234]
  Large language models (LLMs) are shown to possess a wealth of actionable knowledge that can be extracted for robot manipulation. We aim to synthesize robot trajectories for a variety of manipulation tasks given an open-set of instructions and an open-set of objects. We demonstrate how the proposed framework can benefit from online experiences by efficiently learning a dynamics model for scenes that involve contact-rich interactions.
  arXiv  Detail & Related papers  (2023-07-12T07:40:48Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• CLIPort: What and Where Pathways for Robotic Manipulation [35.505615833638124]
  We present CLIPort, a language-conditioned imitation-learning agent that combines the broad semantic understanding with the spatial precision of Transporter. Our framework is capable of solving a variety of language-specified tabletop tasks without any explicit representations of object poses, instance segmentations, memory, symbolic states, or syntactic structures.
  arXiv  Detail & Related papers  (2021-09-24T17:44:28Z)
• Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation [80.29069988090912]
  We study the problem of learning a range of vision-based manipulation tasks from a large offline dataset of robot interaction. We propose to leverage offline robot datasets with crowd-sourced natural language labels. We find that our approach outperforms both goal-image specifications and language conditioned imitation techniques by more than 25%.
  arXiv  Detail & Related papers  (2021-09-02T17:42:13Z)

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.