Negative Shanshui: Real-time Interactive Ink Painting Synthesis
Aven-Le Zhou
TL;DR
Negative Shanshui reimagines classical Shanshui aesthetics to engage audiences with ecological crises in the Anthropocene. The paper presents a real-time, gaze-driven AI synthesis pipeline built on a LoRA-fine-tuned Stable Diffusion model, complemented by inpainting and recursive frame interpolation within a VR environment. Key contributions include the LoRA-based ecological crisis synthesizer, a gaze-responsive morphing mechanism, and a VR hardware-software stack that enables immersive, audience-influenced transformation of landscape imagery. Empirical feedback from a public exhibition reveals a spectrum of affective responses—from empathic urgency to crisis fatigue—and a cyclical narrative of despair giving way to hope, highlighting the potential of AI-enabled aesthetics to prompt reflective engagement with environmental memory. Collectively, the work demonstrates how traditional ecological art can be extended with real-time AI and embodied interaction to foster critical contemplation of human–nature relations in the Anthropocene.
Abstract
This paper presents Negative Shanshui, a real-time interactive AI synthesis approach that reinterprets classical Chinese landscape ink painting, i.e., shanshui, to engage with ecological crises in the Anthropocene. Negative Shanshui optimizes a fine-tuned Stable Diffusion model for real-time inferences and integrates it with gaze-driven inpainting, frame interpolation; it enables dynamic morphing animations in response to the viewer's gaze and presents as an interactive virtual reality (VR) experience. The paper describes the complete technical pipeline, covering the system framework, optimization strategies, gaze-based interaction, and multimodal deployment in an art festival. Further analysis of audience feedback collected during its public exhibition highlights how participants variously engaged with the work through empathy, ambivalence, and critical reflection.