cs.CVNov 9, 2026

WanderBench: Can World Models Explore Dynamic Worlds from Video?

Authors: Yuhang Chen, Jiheng Li, Jiale Wang, Zai Wang, Guangyue Liu

Organizations: Huazhong University of Science and Technology

Abstract

Video world models conditioned on an input video make it possible to explore real, recorded dynamic scenes, enabling re-shooting of footage, free-viewpoint replay, and real-to-sim environments for embodied agents. Such uses require the generated rollout to stay faithful to the recorded world, yet existing benchmarks start from a single image or a text prompt, and video-conditioned generation is evaluated mainly on perceptual quality and camera following. These evaluations do not directly assess whether exploration preserves subject identity, event progression, and scene consistency upon revisiting a location. We introduce WanderBench, a benchmark for exploring dynamic worlds from video. It comprises 745 single-shot source videos of real and AI-generated content in three difficulty tiers (3-25 s), paired with camera routes given as keyboard actions, and evaluates six dimensions with 24 human-validated sub-metrics. Benchmarking eight models, we find that as clips grow longer, models keep the static scene and visual quality but lose camera control and the source dynamics, and that none keeps revisited places consistent. We further propose WanderLand, a training-free framework that conditions each frame of a frozen model on the same-instant source and, on revisits, on its own earlier static content. WanderLand improves five models on every dimension, by up to 8.3 points in source-dynamics fidelity.

Figures & tables

Explore similar work

CardsList
  1. WorldProbe: When Video World Models Fall Apart under Long-Horizon Spatial Exploration

    Oct 29, 2026Minqi Wang, Jie Peng, Hejun Dong +8Video World ModelsWorld Model Evaluation

  2. PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives

    Aug 13, 2026Kaixin Ding, Xi Chen, Minghong Cai +9Long-Horizon Agent EvaluationWorld Model Evaluation

  3. Wonder: Video World Model Done Better

    Jul 28, 2026Jiacong Xu, Hanwen Jiang, Zhixin Shu +3Camera-Controlled Video GenerationReal-Time Interactive Video Generation