arXiv subjects

Yangle Liu

Publications and source records attributed to Yangle Liu.

4 recordsLinked to original sources

arXiv2025

EAST: Environment-Aware Stylized Transition Along the Reality-Virtuality Continuum

In the Virtual Reality (VR) gaming industry, maintaining immersion during real-world interruptions remains a challenge, particularly during transitions along the reality-virtuality continuum (RVC). Existing methods tend to rely on digital replicas or simple visual transitions, neglecting to address the aesthetic discontinuities between real and virtual environments, especially in highly stylized VR games. This paper introduces the Environment-Aware Stylized Transition (EAST) framework, which employs a novel style-transferred 3D Gaussian Splatting (3DGS) technique to transfer real-world interruptions into the virtual environment with seamless aesthetic consistency. Rather than merely transforming the real world into game-like visuals, EAST minimizes the disruptive impact of interruptions by integrating real-world elements within the framework. Qualitative user studies demonstrate significant enhancements in cognitive comfort and emotional continuity during transitions, while quantitative experiments highlight EAST's ability to maintain visual coherence across diverse VR styles.

cs.HC↗

arXiv2025

Endo-G$^{2}$T: Geometry-Guided & Temporally Aware Time-Embedded 4DGS For Endoscopic Scenes

Endoscopic (endo) video exhibits strong view-dependent effects such as specularities, wet reflections, and occlusions. Pure photometric supervision misaligns with geometry and triggers early geometric drift, where erroneous shapes are reinforced during densification and become hard to correct. We ask how to anchor geometry early for 4D Gaussian splatting (4DGS) while maintaining temporal consistency and efficiency in dynamic endoscopic scenes. Thus, we present Endo-G$^{2}$T, a geometry-guided and temporally aware training scheme for time-embedded 4DGS. First, geo-guided prior distillation converts confidence-gated monocular depth into supervision with scale-invariant depth and depth-gradient losses, using a warm-up-to-cap schedule to inject priors softly and avoid early overfitting. Second, a time-embedded Gaussian field represents dynamics in XYZT with a rotor-like rotation parameterization, yielding temporally coherent geometry with lightweight regularization that favors smooth motion and crisp opacity boundaries. Third, keyframe-constrained streaming improves efficiency and long-horizon stability through keyframe-focused optimization under a max-points budget, while non-keyframes advance with lightweight updates. Across EndoNeRF and StereoMIS-P1 datasets, Endo-G$^{2}$T achieves state-of-the-art results among monocular reconstruction baselines.

cs.CV↗

arXiv2025

SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs

Multivariate time series forecasting requires models to simultaneously capture variable-wise structural dependencies and generalize across diverse tasks. While structural encoders are effective in modeling feature interactions, they lack the capacity to support semantic-level reasoning or task adaptation. Conversely, large language models (LLMs) possess strong generalization capabilities but remain incompatible with raw time series inputs. This gap limits the development of unified, transferable prediction systems. Therefore, we introduce SEED, a structural encoder for embedding-driven decoding, which integrates four stages: a token-aware encoder for patch extraction, a projection module that aligns patches with language model embeddings, a semantic reprogramming mechanism that maps patches to task-aware prototypes, and a frozen language model for prediction. This modular architecture decouples representation learning from inference, enabling efficient alignment between numerical patterns and semantic reasoning. Empirical results demonstrate that the proposed method achieves consistent improvements over strong baselines, and comparative studies on various datasets confirm SEED's role in addressing the structural-semantic modeling gap.

cs.CL↗

arXiv2025

CountingFruit: Language-Guided 3D Fruit Counting with Semantic Gaussian Splatting

Accurate 3D fruit counting in orchards is challenging due to heavy occlusion, semantic ambiguity between fruits and surrounding structures, and the high computational cost of volumetric reconstruction. Existing pipelines often rely on multi-view 2D segmentation and dense volumetric sampling, which lead to accumulated fusion errors and slow inference. We introduce FruitLangGS, a language-guided 3D fruit counting framework that reconstructs orchard-scale scenes using an adaptive-density Gaussian Splatting pipeline with radius-aware pruning and tile-based rasterization, enabling scalable 3D representation. During inference, compressed CLIP-aligned semantic vectors embedded in each Gaussian are filtered via a dual-threshold cosine similarity mechanism, retrieving Gaussians relevant to target prompts while suppressing common distractors (e.g., foliage), without requiring retraining or image-space masks. The selected Gaussians are then sampled into dense point clouds and clustered geometrically to estimate fruit instances, remaining robust under severe occlusion and viewpoint variation. Experiments on nine different orchard-scale datasets demonstrate that FruitLangGS consistently outperforms existing pipelines in instance counting recall, avoiding multi-view segmentation fusion errors and achieving up to 99.7% recall on Pfuji-Size_Orch2018 orchard dataset. Ablation studies further confirm that language-conditioned semantic embedding and dual-threshold prompt filtering are essential for suppressing distractors and improving counting accuracy under heavy occlusion. Beyond fruit counting, the same framework enables prompt-driven 3D semantic retrieval without retraining, highlighting the potential of language-guided 3D perception for scalable agricultural scene understanding.

cs.CV↗