Cover Image

MechVerse: Evaluating Physical Motion Consistency in Video Generation Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jain, Rahul, Patel, Mayank, Unmesh, Asim, Ramani, Karthik
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction
by: Patel, Mayank, et al.
Published: (2025)

Exploring Vision-Language Models for Open-Vocabulary Zero-Shot Action Segmentation
by: Unmesh, Asim, et al.
Published: (2026)

ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modeling
by: Zhu, Jiayi, et al.
Published: (2026)

Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos
by: Liu, Jiahe, et al.
Published: (2024)

MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing
by: Hou, Ruibing, et al.
Published: (2025)

M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models
by: Chi, Seunggeun, et al.
Published: (2024)

WonderVerse: Extendable 3D Scene Generation with Video Generative Models
by: Feng, Hao, et al.
Published: (2025)

GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
by: Gu, Leslie, et al.
Published: (2025)

DeepVerse: 4D Autoregressive Video Generation as a World Model
by: Chen, Junyi, et al.
Published: (2025)

Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
by: Shi, Xiaoyu, et al.
Published: (2024)

Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss
by: Zhang, Xinyu, et al.
Published: (2025)

VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?
by: Wang, Zeqing, et al.
Published: (2025)

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
by: Ju, Xuan, et al.
Published: (2025)

CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition
by: Phung, Quynh, et al.
Published: (2025)

MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion
by: Susladkar, Onkar, et al.
Published: (2024)

Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
by: Zhai, Yuanhao, et al.
Published: (2024)

UniVerse-1: Unified Audio-Video Generation via Stitching of Experts
by: Wang, Duomin, et al.
Published: (2025)

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
by: Yang, Yuxue, et al.
Published: (2026)

Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
by: Chi, Seunggeun, et al.
Published: (2024)

HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation
by: Hu, Tao, et al.
Published: (2026)

FC-VFI: Faithful and Consistent Video Frame Interpolation for High-FPS Slow Motion Video Generation
by: Ding, Ganggui, et al.
Published: (2026)

VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control
by: Zheng, Sixiao, et al.
Published: (2026)

WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling
by: Fang, Shaoheng, et al.
Published: (2025)

Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
by: Wang, Chenyu, et al.
Published: (2024)

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
by: Dai, Wenxun, et al.
Published: (2024)

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
by: Chefer, Hila, et al.
Published: (2025)

UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction
by: Cao, Jin, et al.
Published: (2025)

InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition
by: Chi, Seunggeun, et al.
Published: (2023)

Proteus-ID: ID-Consistent and Motion-Coherent Video Customization
by: Zhang, Guiyu, et al.
Published: (2025)

CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
by: Begiristain, León, et al.
Published: (2026)

Physics-Guided Motion Loss for Video Generation Model
by: Xue, Bowen, et al.
Published: (2025)

WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models
by: Inbasekar, Karthik, et al.
Published: (2026)

Temporal Consistency-Aware Text-to-Motion Generation
by: Wang, Hongsong, et al.
Published: (2026)

Intra-finger Variability of Diffusion-based Latent Fingerprint Generation
by: Hussein, Noor, et al.
Published: (2026)

TAIGen: Training-Free Adversarial Image Generation via Diffusion Models
by: Roy, Susim, et al.
Published: (2025)

DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
by: Wen, Kairun, et al.
Published: (2025)

Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy
by: Liu, Yuhao, et al.
Published: (2025)

Narrative Aligned Long Form Video Question Answering
by: Jain, Rahul, et al.
Published: (2026)

MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models
by: Lee, Young-Jun, et al.
Published: (2025)

Occlusion-Aware Temporally Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction
by: Doh, Hyungjun, et al.
Published: (2025)