GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning

• URL: http://arxiv.org/abs/2609.05927v2
• Date: Thu, 10 Sep 2026 05:59:34 GMT
• Title: GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning
• Abstract summary: We present GIF, an agentic Generation framework for Interactive and Functional object compositions.<n>GIF improves both asset quality and relation matching, while reducing collision rate to below 1%.<n>We synthesize data for policy learning, revealing diversity scaling in both simulation and real-world deployment.
• Score: 15.060587346990792
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Robot manipulation foundation models require scalable evaluation and data generation across diverse scenarios, with simulation providing an environment for both. Automated scene generation offers a promising path, yet prior work has largely emphasized coarse-grained scene layouts rather than fine-grained functional object compositions. Motivated by this gap, we present GIF, an agentic Generation framework for Interactive and Functional object compositions. In this framework, we recast this problem as disentangled reconstruction followed by relative pose recovery. CoGen produces instance-disentangled meshes with coarse initial poses leveraging complementary strengths of 2D and 3D generative models. GPRM refines the relative pose under joint geometric and physical guidance, and a VLM verifier selects the candidate that best matches the structured specification. We further construct a benchmark spanning eight representative contact-geometry classes and compare with state-of-the-art generators; GIF improves both asset quality and relation matching, while reducing collision rate to below 1%. Finally, we synthesize data for policy learning, revealing diversity scaling in both simulation and real-world deployment.

Related papers

• URDF-Anything+: Autoregressive Articulated 3D Models Generation for Physical Simulation [45.4820195450296]
  We present an end-to-end autoregressive framework that directly generates executable articulated object models from visual observations.<n>Building on this capability, we enable a new Real-Follow-Sim paradigm, where high-fidelity digital twins constructed from visual observations allow policies trained in simulation to transfer to real robots without online adaptation.
  arXiv  Detail & Related papers  (2026-03-14T16:23:44Z)
• AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation [45.753757870577196]
  We introduce AGILE, a robust framework that shifts the paradigm from reconstruction to agentic generation for interaction learning.<n>We show that AGILE outperforms baselines in global geometric accuracy while demonstrating exceptional robustness on challenging sequences where prior art frequently collapses.
  arXiv  Detail & Related papers  (2026-02-04T15:42:58Z)
• UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass [83.7071371474926]
  UniSH is a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction.<n>Our framework bridges strong, disparate priors from scene reconstruction and HMR.<n>Our model achieves state-of-the-art performance on human-centric scene reconstruction.
  arXiv  Detail & Related papers  (2026-01-03T16:06:27Z)
• SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge [22.64986854574998]
  Articulated 3D objects are critical for embodied AI, robotics, and interactive scene understanding.<n>We introduce SPARK, a framework for reconstructing physically consistent, kinematic part-level articulated objects from a single RGB image.
  arXiv  Detail & Related papers  (2025-12-01T12:51:56Z)
• Asset-Driven Sematic Reconstruction of Dynamic Scene with Multi-Human-Object Interactions [41.29588736908775]
  3D geometry modeling of dynamic scenes is crucial for applications like AR/VR, gaming, and embodied AI.<n>We propose a hybrid approach that combines the advantages of 1) 3D generative models for generating high-fidelity meshes of the scene elements, 2) Semantic-aware deformation, and 3) GS-based optimization of the individual elements.<n>Our method outperforms the state-of-the-art method in producing better surface reconstruction of such scenes.
  arXiv  Detail & Related papers  (2025-11-29T16:36:22Z)
• Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects [59.51185639557874]
  We introduce Kinematify, an automated framework that synthesizes articulated objects directly from arbitrary RGB images or textual descriptions.<n>Our method addresses two core challenges: (i) inferring kinematic topologies for high-DoF objects and (ii) estimating joint parameters from static geometry.
  arXiv  Detail & Related papers  (2025-11-03T07:21:42Z)
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model [76.08429266631823]
  We propose an end-to-end automatic reconstruction framework based on a 3D multimodal large language model (MLLM)<n>URDF-Anything utilizes an autoregressive prediction framework based on point-cloud and text multimodal input to jointly optimize geometric segmentation and kinematic parameter prediction.<n> Experiments on both simulated and real-world datasets demonstrate that our method significantly outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-11-02T13:45:51Z)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)
• Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection [116.21529970404653]
  We introduce SG2HOI+, a unified one-step model based on the Transformer architecture. Our approach employs two interactive hierarchical Transformers to seamlessly unify the tasks of SGG and HOI detection. Our approach achieves competitive performance when compared to state-of-the-art HOI methods.
  arXiv  Detail & Related papers  (2023-11-03T07:25:57Z)
• Object-Centric Image Generation from Layouts [93.10217725729468]
  We develop a layout-to-image-generation method to generate complex scenes with multiple objects. Our method learns representations of the spatial relationships between objects in the scene, which lead to our model's improved layout-fidelity. We introduce SceneFID, an object-centric adaptation of the popular Fr'echet Inception Distance metric, that is better suited for multi-object images.
  arXiv  Detail & Related papers  (2020-03-16T21:40:09Z)

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.