SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics

arXiv 2026 67.2 method, application

TLDR

SurgVista introduces a surgical world model with deformation consistency and drift adaptation to generate long-horizon, action-conditioned future frames with plausible instrument-tissue dynamics.

Reasoning

The paper directly addresses two key failure modes in surgical world models—spatial interaction incoherence and temporal fidelity collapse—through novel training recipes and introduces a new benchmark (SurgWorld-Bench) for evaluation. Strengths include clear problem formulation, methodological contributions, and strong empirical results; weaknesses are the narrow surgical domain focus and lack of explicit discussion on generalization or limitations.

Read-first score

Read-first score 67.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 60.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Citation impact 18%

94.4

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.9437282

Topical relevance 29%

85.7

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,evaluation,experiment,metric

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FoundationFrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 429.

Keyword Scores

world model

generative world model

interactive world model

video world model

world dynamics prediction

world simulator

model-based reinforcement learning world model

Deep Analysis

Innovations

Deformation Consistency Regularization: extracts scene-point trajectories from training videos and enforces cross-frame coherence through latent contrastive learning to strengthen physically consistent instrument-tissue dynamics.
Drift Adaptation Training: perturbs conditioning frames with online prediction residuals and photometric augmentations calibrated to long-horizon drift statistics to sustain visual fidelity over extended rollouts.
SurgWorld-Bench: a new benchmark featuring diverse procedure types, long-range rollouts, and decoupled metrics for instrument-motion accuracy and tissue-response fidelity.

Methodology

SurgVista is a surgical world model that uses two training recipes: Deformation Consistency Regularization, which applies contrastive learning on scene-point trajectories from training videos to enforce cross-frame coherence, and Drift Adaptation Training, which perturbs conditioning frames with prediction residuals and photometric augmentations calibrated to long-horizon drift statistics. The model is evaluated on the introduced SurgWorld-Bench benchmark against state-of-the-art methods using metrics for visual quality, temporal consistency, and interaction fidelity.

Key Results

SurgVista consistently outperforms state-of-the-art methods across visual quality, temporal consistency, and interaction fidelity, with performance gains widening as the prediction horizon grows.

Resources

Paper