LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)

TL;DR

The LoViF 2026 PhyScore challenge evaluates holistic quality of generated videos across multiple dimensions, emphasizing physical plausibility, temporal coherence, and anomaly detection in diverse scenarios.

Contribution

First comprehensive benchmark and challenge for assessing multi-dimensional quality and physical realism in 4D world model-generated videos.

Findings

Participants developed metrics predicting four quality dimensions.

Benchmark dataset includes 1,554 videos across physics-relevant scenarios.

Evaluation combines score prediction and anomaly localization.

Abstract

This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D generation settings. The challenge is motivated by a central gap in current evaluation practice: perceptual quality alone is insufficient to judge whether generated dynamics are physically plausible, temporally coherent, and consistent with input conditions. Participants are required to build a metric that jointly predicts four dimensions, i.e., Video Quality, Physical Realism, Condition-Video Alignment, and Temporal Consistency. Depart from that, participants also need to localize physical anomaly timestamps for fine-grained diagnosis. The benchmark dataset contains 1,554 videos generated by seven representative world generative models, organized into three tracks (text-2D, image-to-4D, and video-to-4D) and spanning 26 categories. These categories explicitly cover physics-relevant scenarios, including dynamics, optics, and thermodynamics, together with diverse real-world and creative content. To ensure label reliability, scores and anomaly timestamps are produced through trained human annotation with an additional automated quality-control pass. Evaluation is based on both score prediction and anomaly localization, with a composite protocol that combines TimeStamp_IOU and SRCC/PLCC. This report summarizes the challenge design and provides method-level insights from submitted solutions.