SearcharxivSearch

arXiv subjects

Biao Zhu

Publications and source records attributed to Biao Zhu.

3 recordsLinked to original sources

Reviving Ancient Paintings via Poem: A Colorization Framework for Aligning Cultural Semantics

The irreversible fading of ancient paintings disrupts the "congruence between poems and paintings", a core aesthetic principle where visual imagery harmonizes with literary inscriptions. Although diffusion models provide strong generative priors, restoring historically faithful colors remains difficult: visual restoration is inherently ambiguous, while direct text guidance often causes modern semantic bias, over-saturation, and cross-boundary color leakage. To address this, we propose PoemColor, a poem-guided ancient painting colorization framework. Our method aligns poetic cultural semantics with painting restoration through two key designs. First, the Poetic Painting Projector (P3) converts implicit poetic context into a classical color-aware condition via poem-to-palette pretraining, reducing the ambiguity of poem-to-color mapping. Second, Structure-Aware Semantic Attention (SASA) regulates how poetic color semantics are injected into the diffusion backbone by jointly controlling their propagation direction and regional injection strength. In addition, we construct a hybrid restoration dataset that integrates synthetic degradation with expert-restored artifacts, providing both scalable supervision and real classical color references. Extensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods, delivering controllable colorization that revives both historical authenticity and poetic semantics.

cs.CV

VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation

Data visualization generation using Large Language Models (LLMs) has shown promising results but often produces suboptimal visualizations that require human intervention for improvement. In this work, we introduce VIS-Shepherd, a specialized Multimodal Large Language Model (MLLM)-based critic to evaluate and provide feedback for LLM-generated data visualizations. At the core of our approach is a framework to construct a high-quality visualization critique dataset, where we collect human-created visualization instances, synthesize corresponding LLM-generated instances, and construct high-quality critiques. We conduct both model-based automatic evaluation and human preference studies to evaluate the effectiveness of our approach. Our experiments show that even small (7B parameters) open-source MLLM models achieve substantial performance gains by leveraging our high-quality visualization critique dataset, reaching levels comparable to much larger open-source or even proprietary models. Our work demonstrates significant potential for MLLM-based automated visualization critique and indicates promising directions for enhancing LLM-based data visualization generation. Our project page: https://github.com/bopan3/VIS-Shepherd.

cs.CV

The long-lasting optical afterglow plateau of short burst GRB 130912A

The short burst GRB 130912A was detected by Swift, Fermi satellites and several ground-based optical telescopes. Its X-ray light curve decayed with time normally. The optical emission, however, displayed a long term plateau, which is the longest one in current short GRB observations. In this work we examine the physical origin of the X-ray and optical emission of this peculiar event. We find that the canonical forward shock afterglow emission model can account for the X-ray and optical data self-consistently and the energy injection model that has been widely adopted to interpret the shallowly-decaying afterglow emission is not needed. We also find that the burst was born in a very-low density interstellar medium, consistent with the compact object merger model. Significant fractions of the energy of the forward shock have been given to accelerate the non-thermal electrons and amplify the magnetic fields (i.e., $ε_{\rm e}\sim 0.37$ and $ε_{\rm B}\sim 0.16$, respectively), which are much larger than those inferred in most short burst afterglow modeling and can explain why the long-lasting optical afterglow plateau is rare in short GRBs.

astro-ph.HE