arXiv subjects

Lanshan He

Publications and source records attributed to Lanshan He.

7 recordsLinked to original sources

arXiv2026

Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment

This paper presents Native3D, the first end-to-end 3D scene generation framework that completely bypasses 2D intermediate representations. Traditional approaches typically require adapting 3D representations to the 2D domain to leverage pre-trained diffusion models, which inevitably introduces domain adaptation issues including geometric structural distortion and texture detail degradation. To address these limitations, we design a unified mesh-texture joint representation that simultaneously models both geometric structures and texture features through a Transformer-based scene encoder, effectively maintaining spatial relationships and visual consistency among objects within scenes. We further propose the 3D Representation Alignment Loss (3D REPA Loss), which employs an improved contrastive learning mechanism to align multi-level semantic representations in the latent space, significantly enhancing geometric and textural fidelity. Experimental results demonstrate that Native3D outperforms existing methods in both generation quality and editing flexibility, providing a novel solution for 3D scene editing.

cs.CV↗

arXiv2026

Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation

Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative delivery, character development, and emotional engagement. Producing cutscenes is inherently complex: it demands seamless coordination across screenwriting, cinematography, character animation, voice acting, and technical direction, often requiring days to weeks of collaborative effort from multidisciplinary teams to produce minutes of polished content. In this work, we present Cutscene Agent, an LLM agent framework for automated end-to-end cutscene generation. The framework makes three contributions: (1)~a Cutscene Toolkit built on the Model Context Protocol (MCP) that establishes \emph{bidirectional} integration between LLM agents and the game engine -- agents not only invoke engine operations but continuously observe real-time scene state, enabling closed-loop generation of editable engine-native cinematic assets; (2)~a multi-agent system where a director agent orchestrates specialist subagents for animation, cinematography, and sound design, augmented by a visual reasoning feedback loop for perception-driven refinement; and (3)~CutsceneBench, a hierarchical evaluation benchmark for cutscene generation. Unlike typical tool-use benchmarks that evaluate short, isolated function calls, cutscene generation requires long-horizon, multi-step orchestration of dozens of interdependent tool invocations with strict ordering constraints -- a capability dimension that existing benchmarks do not cover. We evaluate a range of LLMs on CutsceneBench and analyze their performance across this challenging task.

cs.GR↗

arXiv2025

Global Position Aware Group Choreography using Large Language Model

Dance serves as a profound and universal expression of human culture, conveying emotions and stories through movements synchronized with music. Although some current works have achieved satisfactory results in the task of single-person dance generation, the field of multi-person dance generation remains relatively novel. In this work, we present a group choreography framework that leverages recent advancements in Large Language Models (LLM) by modeling the group dance generation problem as a sequence-to-sequence translation task. Our framework consists of a tokenizer that transforms continuous features into discrete tokens, and an LLM that is fine-tuned to predict motion tokens given the audio tokens. We show that by proper tokenization of input modalities and careful design of the LLM training strategies, our framework can generate realistic and diverse group dances while maintaining strong music correlation and dancer-wise consistency. Extensive experiments and evaluations demonstrate that our framework achieves state-of-the-art performance.

cs.GR↗

arXiv2024

LLM Gesticulator: Leveraging Large Language Models for Scalable and Controllable Co-Speech Gesture Synthesis

In this work, we present LLM Gesticulator, an LLM-based audio-driven co-speech gesture generation framework that synthesizes full-body animations that are rhythmically aligned with the input audio while exhibiting natural movements and editability. Compared to previous work, our model demonstrates substantial scalability. As the size of the backbone LLM model increases, our framework shows proportional improvements in evaluation metrics (a.k.a. scaling law). Our method also exhibits strong controllability where the content, style of the generated gestures can be controlled by text prompt. To the best of our knowledge, LLM gesticulator is the first work that use LLM on the co-speech generation task. Evaluation with existing objective metrics and user studies indicate that our framework outperforms prior works.

cs.GR↗

arXiv2023

Intergrated Segmentation and Detection Models for Dentex Challenge 2023

Dental panoramic x-rays are commonly used in dental diagnosing. With the development of deep learning, auto detection of diseases from dental panoramic x-rays can help dentists to diagnose diseases more efficiently.The Dentex Challenge 2023 is a competition for automatic detection of abnormal teeth along with their enumeration ids from dental panoramic x-rays. In this paper, we propose a method integrating segmentation and detection models to detect abnormal teeth as well as obtain their enumeration ids.Our codes are available at https://github.com/xyzlancehe/DentexSegAndDet.

cs.CV↗

arXiv2023

DENTEX: Dental Enumeration and Tooth Pathosis Detection Benchmark for Panoramic X-ray

Panoramic X-rays are frequently used in dentistry for treatment planning, but their interpretation can be both time-consuming and prone to error. Artificial intelligence (AI) has the potential to aid in the analysis of these X-rays, thereby improving the accuracy of dental diagnoses and treatment plans. Nevertheless, designing automated algorithms for this purpose poses significant challenges, mainly due to the scarcity of annotated data and variations in anatomical structure. To address these issues, we organized the Dental Enumeration and Diagnosis on Panoramic X-rays Challenge (DENTEX) in association with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) in 2023. This challenge aims to promote the development of algorithms for multi-label detection of abnormal teeth, using three types of hierarchically annotated data: partially annotated quadrant data, partially annotated quadrant-enumeration data, and fully annotated quadrant-enumeration-diagnosis data, inclusive of four different diagnoses. In this paper, we present a comprehensive analysis of the methods and results from the challenge. Our findings reveal that top performers succeeded through diverse, specialized strategies, from segmentation-guided pipelines to highly-engineered single-stage detectors, using advanced Transformer and diffusion models. These strategies significantly outperformed traditional approaches, particularly for the challenging tasks of tooth enumeration and subtle disease classification. By dissecting the architectural choices that drove success, this paper provides key insights for future development of AI-powered tools that can offer more precise and efficient diagnosis and treatment planning in dentistry. The evaluation code and datasets can be accessed at https://github.com/ibrahimethemhamamci/DENTEX

cs.CV↗

arXiv2023

Self-doping effect in confined copper selenide semiconducting quantum dots for efficient photoelectrocatalytic oxygen evolution

Self-doping can not only suppress the photogenerated charge recombination of semiconducting quantum dots by self-introducing trapping states within the bandgap, but also provide high-density catalytic active sites as the consequence of abundant non-saturated bonds associated with the defects. Here, we successfully prepared semiconducting copper selenide (CuSe) confined quantum dots with abundant vacancies and systematically investigated their photoelectrochemical characteristics. Photoluminescence characterizations reveal that the presence of vacancies reduces the emission intensity dramatically, indicating a low recombination rate of photogenerated charge carriers due to the self-introduced trapping states within the bandgap. In addition, the ultra-low charge transfer resistance measured by electrochemical impedance spectroscopy implies the efficient charge transfer of CuSe semiconducting quantum dots-based photoelectrocatalysts, which is guaranteed by the high conductivity of their confined structure as revealed by room-temperature electrical transport measurements. Such high conductivity and low photogenerated charge carriers recombination rate, combined with high-density active sites and confined structure, guaranteeing the remarkable photoelectrocatalytic performance and stability as manifested by photoelectrocatalysis characterizations. This work promotes the development of semiconducting quantum dots-based photoelectrocatalysis and demonstrates CuSe semiconducting quantum confined catalysts as an advanced photoelectrocatalysts for oxygen evolution reaction.

cond-mat.mtrl-sci↗