MOSIV: Multi-Object System Identification from Videos

• URL: http://arxiv.org/abs/2603.06022v1
• Date: Fri, 06 Mar 2026 08:16:16 GMT
• Title: MOSIV: Multi-Object System Identification from Videos
• Abstract summary: We propose a new framework that directly optimize for continuous, per-object material parameters using a differentiable simulator guided by geometric objectives derived from video.<n>We also present a new synthetic benchmark with contact-rich, multi-object interactions to facilitate evaluation.
• Score: 54.53609234233857
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce the challenging problem of multi-object system identification from videos, for which prior methods are ill-suited due to their focus on single-object scenes or discrete material classification with a fixed set of material prototypes. To address this, we propose MOSIV, a new framework that directly optimizes for continuous, per-object material parameters using a differentiable simulator guided by geometric objectives derived from video. We also present a new synthetic benchmark with contact-rich, multi-object interactions to facilitate evaluation. On this benchmark, MOSIV substantially improves grounding accuracy and long-horizon simulation fidelity over adapted baselines, establishing it as a strong baseline for this new task. Our analysis shows that object-level fine-grained supervision and geometry-aligned objectives are critical for stable optimization in these complex, multi-object settings. The source code and dataset will be released.

Related papers

• High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians [38.0162622592412]
  We propose a novel system for the robust and accurate reconstruction of hands and objects from synchronized and calibrated multi-view videos.<n>Our pipeline achieves highly robust, artifact-free reconstruction, providing an efficient foundation for automated 4D asset generation.
  arXiv  Detail & Related papers  (2026-06-14T16:36:49Z)
• ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions [48.84720445548848]
  ArtHOI is an optimization-based framework that integrates and refines priors from multiple foundation models.<n>In particular, we introduce an Adaptive Sampling Refinement (ASR) method to optimize object's metric scale.<n>We also propose a Multimodal Large Language Model (MLLM) guided hand-object alignment method.
  arXiv  Detail & Related papers  (2026-03-26T18:00:17Z)
• Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning [51.170479006249195]
  We introduce a new dataset, benchmark, and a dynamic coarse-to-fine learning scheme in this study.<n>Our proposed dataset, AI-TOD-R, features the smallest object sizes among all oriented object detection datasets.<n>We present a benchmark spanning a broad range of detection paradigms, including both fully-supervised and label-efficient approaches.
  arXiv  Detail & Related papers  (2024-12-16T09:14:32Z)
• MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes [35.16430027877207]
  MOVIS aims to enhance the structural awareness of the view-conditioned diffusion model for multi-object NVS.<n>We introduce an auxiliary task requiring the model to simultaneously predict novel view object masks.<n>Our method exhibits strong generalization capabilities and produces consistent novel view synthesis.
  arXiv  Detail & Related papers  (2024-12-16T05:23:45Z)
• Appearance-Based Refinement for Object-Centric Motion Segmentation [85.2426540999329]
  We introduce an appearance-based refinement method that leverages temporal consistency in video streams to correct inaccurate flow-based proposals. Our approach involves a sequence-level selection mechanism that identifies accurate flow-predicted masks as exemplars. Its performance is evaluated on multiple video segmentation benchmarks, including DAVIS, YouTube, SegTrackv2, and FBMS-59.
  arXiv  Detail & Related papers  (2023-12-18T18:59:51Z)
• Scalable Video Object Segmentation with Identification Mechanism [125.4229430216776]
  This paper explores the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object (VOS) We present two innovative approaches, Associating Objects with Transformers (AOT) and Associating Objects with Scalable Transformers (AOST) Our approaches surpass the state-of-the-art competitors and display exceptional efficiency and scalability consistently across all six benchmarks.
  arXiv  Detail & Related papers  (2022-03-22T03:33:27Z)
• Benchmarking Unsupervised Object Representations for Video Sequences [111.81492107649889]
  We compare the perceptual abilities of four object-centric approaches: ViMON, OP3, TBA and SCALOR. Our results suggest that the architectures with unconstrained latent representations learn more powerful representations in terms of object detection, segmentation and tracking. Our benchmark may provide fruitful guidance towards learning more robust object-centric video representations.
  arXiv  Detail & Related papers  (2020-06-12T09:37:24Z)

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.