paper-with-me

홈 › Papers

VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation

2026-07-26 · Tianxiao Chen, Hanmo Chen, Huajin Chen, Bo Li, Qi Ye, Peng-Tao Jiang arxiv

Modern video generation models can synthesize visually compelling and temporally coherent clips, yet controlling their physical behavior remains difficult with standard text and image conditions. The core challenge is a conditioning bottleneck: material response, contact interaction, deformation, and motion trajectory are continuous and relational physical cues that are hard to specify exhaustively in language but can be demonstrated naturally by video. We propose VIPER, a Visual In-Context Physics Reasoning framework for reference-guided image-to-video generation. Given a target image, a brief target prompt, and a reference video, VIPER treats the reference as a dense visual demonstration of the desired physical process rather than an appearance template. It uses a Multimodal Large Language Model (MLLM) to extract reference-derived physical cues and guide a pretrained image-to-video generator through a hierarchical training strategy, enabling physical behavior transfer while preserving the visual prior of the base generator. To support this setting, we construct VIPER-19K, a curated dataset with material, trajectory, and physical-impact annotations, together with filtered reference-target pairs. Experiments on an unseen validation set show that VIPER achieves stronger reference-video physical similarity and higher human preference than representative video generation and video-as-prompt baselines, while maintaining competitive general video quality. Qualitative results further demonstrate that VIPER can transfer reference-derived physical behavior to new target scenes without requiring carefully engineered prompts.

📄 PDF Abstract BibTeX arXiv:2607.23472

Code (2)

iszhanjiawei/video-to-audio-arxiv-daily
liutaocode/Video-Generation-arxiv-daily ★ 11

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery

2025-08-24 · Jiaqi Liu, Songning Lai, Pengze Li, Di Yu 외 arxiv

Automated discovery of physical laws from observational data in the real world is a grand challenge in AI. Current methods, relying on symbolic regression or LLMs, are limited to uni-modal data and overlook the rich, vis…

Reinforcement Learning

VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making

2025-03-19 · Mohamed Salim Aissi, Clemence Grislain, Mohamed Chetouani, Olivier Sigaud 외

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely ope…

Decision MakingSequential Decision Making

VIPER Strike: Defeating Visual Reasoning CAPTCHAs via Structured Vision-Language Inference

2026-01-10 · Minfeng Qi, Dongyang He, Qin Wang, Lefeng Zhang arxiv

Visual Reasoning CAPTCHAs (VRCs) combine visual scenes with natural-language queries that demand compositional inference over objects, attributes, and spatial relations. They are increasingly deployed as a primary defens…

Visual Reasoning

Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning

2025-12-31 · Yifan Li, Yukai Gu, Yingqian Min, Zikang Liu 외 arxiv

Recent breakthroughs in video generation have demonstrated an emerging capability termed Chain-of-Frames (CoF) reasoning, where models resolve complex tasks through the generation of continuous frames. While these models…

Visual ReasoningVideo Generation

ViperGPT: Visual Inference via Python Execution for Reasoning

2023-03-14 · ICCV 2023 1 · Dídac Surís, Sachit Menon, Carl Vondrick

Answering visual queries is a complex task that requires both visual processing and reasoning. End-to-end models, the dominant approach for this task, do not explicitly differentiate between the two, limiting interpretab…

Code GenerationVideo Question AnsweringZero-Shot Video Question Answer