cs.CV（2025-01-29）

📊 共 13 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (7 篇)

#题目一句话要点标签🔗⭐
1 VoD-3DGS: View-opacity-Dependent 3D Gaussian Splatting 提出视角-不透明度相关的3D高斯溅射，用于增强视角依赖渲染效果 3D gaussian splatting 3DGS gaussian splatting
2 FeatureGS: Eigenvalue-Feature Optimization in 3D Gaussian Splatting for Geometrically Accurate and Artifact-Reduced Reconstruction FeatureGS：基于特征值优化的3D高斯溅射，实现几何精确和伪影减少的重建 3D gaussian splatting 3DGS gaussian splatting
3 CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering CrowdSplat：探索高斯溅射在人群渲染中的应用，实现高质量实时渲染。 3D gaussian splatting gaussian splatting splatting
4 Efficient Redundancy Reduction for Open-Vocabulary Semantic Segmentation ERR-Seg：通过减少冗余信息，高效解决开放词汇语义分割问题 open-vocabulary open vocabulary
5 HOMER: Homography-Based Efficient Multi-view 3D Object Removal HOMER：基于单应性的高效多视角3D物体移除方法 3D gaussian splatting gaussian splatting splatting
6 SSF: Sparse Long-Range Scene Flow for Autonomous Driving 提出基于稀疏卷积的长程场景流方法SSF，提升自动驾驶感知能力。 scene flow ✅
7 3D Reconstruction of Shoes for Augmented Reality 提出基于3D高斯溅射的移动端鞋类3D重建与AR展示方案，提升在线购物体验 3D gaussian splatting gaussian splatting splatting

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
8 Multimodal Large Language Models for Image, Text, and Speech Data Augmentation: A Survey 综述：多模态大语言模型在图像、文本和语音数据增强中的应用 large language model multimodal ✅
9 LFTR: Learning-Free Token Reduction for Multimodal Large Language Models 提出一种免训练的视觉Token缩减方法LFTR，用于加速多模态大语言模型推理。 large language model multimodal
10 Robust Multimodal Learning via Cross-Modal Proxy Tokens 提出跨模态代理令牌(CMPT)，增强多模态模型在模态缺失情况下的鲁棒性。 multimodal ✅
11 Technical report on label-informed logit redistribution for better domain generalization in low-shot classification with foundation models 提出信心错位惩罚以改善低样本分类的领域泛化问题 foundation model
12 General Scene Adaptation for Vision-and-Language Navigation 提出GSA-VLN以解决视觉-语言导航中的环境适应问题 VLN

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
13 Glioma Multimodal MRI Analysis System for Tumor Layered Diagnosis via Multi-task Semi-supervised Learning 提出GMMAS：基于多任务半监督学习的脑胶质瘤多模态MRI分层诊断系统 contrastive learning distillation multimodal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页