MechVerse: Evaluating Physical Motion Consistency in Video Generation Models

• URL: http://arxiv.org/abs/2605.14843v1
• Date: Thu, 14 May 2026 13:48:17 GMT
• Title: MechVerse: Evaluating Physical Motion Consistency in Video Generation Models
• Abstract summary: MechVerse is a benchmark for mechanically consistent image-to-video generation.<n>We evaluate proprietary, open-source, and fine-tuned image-to-video models using standard video metrics.<n>Results show that current models can preserve appearance and smoothness while failing to generate mechanically admissible motion.
• Score: 12.882634043776507
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text- and image-conditioned video generation models have achieved strong visual fidelity and temporal coherence, but they often fail to generate motion governed by kinematic and geometric constraints. In these settings, object parts must remain rigid, maintain contact or coupling with neighboring components, and transfer motion consistently across connected parts. These requirements are especially explicit in articulated mechanical assemblies, where motion is constrained by rigid-link geometry, contact/coupling relations, and transmission through kinematic chains. A generated video may therefore appear plausible while violating the intended mechanism, such as rotating a part that should translate, deforming a rigid component, breaking coupling between parts, or failing to move downstream components. To evaluate this gap, We introduce MechVerse, a benchmark for mechanically consistent image-to-video generation. MechVerse contains 21,156 synthetic clips from 1,357 mechanical assemblies across 141 categories, organized into three tiers of increasing kinematic complexity: independent articulation, pairwise coupling, and densely coupled multi-part mechanisms. Each clip is paired with a structured prompt describing part identities, stationary supports, moving components, motion primitives, direction, speed/extent, and inter-part dependencies. We evaluate proprietary, open-source, and fine-tuned image-to-video models using standard video metrics, instruction-following scores, and human judgments of motion correctness and kinematic coupling. Results show that current models can preserve appearance and smoothness while failing to generate mechanically admissible motion, with errors increasing as coupling complexity grows. MechVerse provides a benchmark for measuring and improving mechanism-aware video generation from image and language inputs.

Related papers

• Articulated Object Reconstruction from Rest-State Observation [33.09154459685742]
  Building interactive digital twins requires recovering both 3D geometry and the kinematic structures that govern how objects articulate.<n>We introduce a rest-state formulation that reconstructs articulated objects from a single closed configuration.
  arXiv  Detail & Related papers  (2026-07-30T06:42:03Z)
• Tempered Self-Similarity Alignment for Physically Plausible Video Generation [83.40337664171939]
  Self-similarity loss transforms into probabilistic correspondence and trains the video generative model to align its correspondence with those of the visual foundation model on dynamically changing regions.<n>Our method demonstrates substantial improvements in physical plausibility across diverse interaction scenarios, validating the effectiveness of transferring relational knowledge for video generation.
  arXiv  Detail & Related papers  (2026-05-24T09:28:05Z)
• Learning Reactive Human Motion Generation from Paired Interaction Data Using Transformer-Based Models [0.0]
  This study addresses the problem of generating the motion of one person based on the motion of another in interaction scenarios.<n>We implement and compare three models: a simple Transformer, iTransformer, and Crossformer.<n> Experimental results show that the simple Transformer can generate plausible interaction-aware motions without suffering from posture collapse.
  arXiv  Detail & Related papers  (2026-04-24T02:27:13Z)
• HECTOR: Hybrid Editable Compositional Object References for Video Generation [23.216951224722127]
  HECTOR is a generative pipeline that enables fine-grained compositional control.<n>It supports hybrid reference conditioning, allowing generation to be simultaneously guided by static images and/or dynamic videos.<n>It achieves superior visual quality, stronger reference preservation, and improved motion controllability compared with existing approaches.
  arXiv  Detail & Related papers  (2026-03-09T19:09:40Z)
• PAct: Part-Decomposed Single-View Articulated Object Generation [45.04652409374895]
  Articulated objects are central to interactive 3D applications, including embodied AI, robotics, and VR/AR.<n>We introduce a part-centric generative framework for articulated object creation that synthesizes part geometry, composition, and articulation under explicit part-aware conditioning.<n>Our representation models an object as a set of movable parts, each encoded by latent tokens augmented with part identity and articulation cues.
  arXiv  Detail & Related papers  (2026-02-16T17:45:44Z)
• SpriteHand: Real-Time Versatile Hand-Object Interaction with Autoregressive Video Generation [64.3409486422946]
  We present SpriteHand, an autoregressive video generation framework for real-time synthesis of hand-object interaction videos.<n>Our model employs a causal inference architecture for autoregressive generation and leverages a hybrid post-training approach to enhance visual realism and temporal coherence.<n> Experiments demonstrate superior visual quality, physical plausibility, and interaction fidelity compared to both generative and engine-based baselines.
  arXiv  Detail & Related papers  (2025-12-01T18:13:40Z)
• VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video [60.63575135514847]
  Building digital twins of articulated objects from monocular video presents an essential challenge in computer vision.<n>We introduce VideoArtGS, a novel approach that reconstructs high-fidelity digital twins of articulated objects from monocular video.<n>VideoArtGS demonstrates state-of-the-art performance in articulation and mesh reconstruction, reducing the reconstruction error by about two orders of magnitude compared to existing methods.
  arXiv  Detail & Related papers  (2025-09-22T11:52:02Z)
• DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction [12.882634043776507]
  We introduce MechBench, a benchmark dataset of 693 diverse synthetic gear assemblies with part-wise ground-truth motion trajectories.<n>We propose DYNAMO, a dependency-aware neural model that predicts per-part SE(3) motion trajectories directly from segmented CAD point clouds.<n>Together, MechBench and DYNAMO establish a novel systematic framework for data-driven learning of coupled mechanical motion in CAD assemblies.
  arXiv  Detail & Related papers  (2025-09-15T20:32:56Z)
• Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting [9.432567695900184]
  Part$2$GS is a novel framework for modeling articulated digital twins of multi-part objects with high-fidelity geometry.<n>To ensure physically consistent motion, we propose a motion-aware canonical representation guided by physics-based constraints.<n>We show that Part$2$GS consistently outperforms state-of-the-art methods by up to 10$times$ in Chamfer Distance for movable parts.
  arXiv  Detail & Related papers  (2025-06-20T17:59:12Z)
• VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models [71.9811050853964]
  VideoJAM is a novel framework that instills an effective motion prior to video generators.<n>VideoJAM achieves state-of-the-art performance in motion coherence.<n>These findings emphasize that appearance and motion can be complementary and, when effectively integrated, enhance both the visual quality and the coherence of video generation.
  arXiv  Detail & Related papers  (2025-02-04T17:07:10Z)
• InterDyn: Controllable Interactive Dynamics with Video Diffusion Models [50.38647583839384]
  We propose InterDyn, a framework that generates videos of interactive dynamics given an initial frame and a control signal encoding the motion of a driving object or actor.<n>Our key insight is that large video generation models can act as both neurals and implicit physics simulators'', having learned interactive dynamics from large-scale video data.
  arXiv  Detail & Related papers  (2024-12-16T13:57:02Z)
• TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation [97.96178992465511]
  We argue that generated videos should incorporate the emergence of new concepts and their relation transitions like in real-world videos as time progresses. To assess the Temporal Compositionality of video generation models, we propose TC-Bench, a benchmark of meticulously crafted text prompts, corresponding ground truth videos, and robust evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-12T21:41:32Z)

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.