cs.CV（2025-05-04）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (8 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (8 篇)

#题目一句话要点标签🔗⭐
1 SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting SparSplat：基于可泛化2D高斯溅射的快速多视角重建，实现稀疏视角下的高质量三维重建与新视角合成。 3D gaussian splatting 3DGS gaussian splatting
2 SignSplat: Rendering Sign Language via Gaussian Splatting SignSplat：通过高斯溅射渲染手语，提升复杂手部和面部动作的建模精度 gaussian splatting splatting human motion
3 GarmentGS: Point-Cloud Guided Gaussian Splatting for High-Fidelity Non-Watertight 3D Garment Reconstruction GarmentGS：点云引导的高保真非封闭3D服装重建 3D gaussian splatting gaussian splatting splatting
4 Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation 利用交互式分割基准评估视觉基础模型特征上采样方法 scene understanding foundation model multimodal ✅
5 Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance Fields 提出Switch-NeRF++，通过异构混合专家网络高效学习大规模场景的神经辐射场。 NeRF neural radiance field ✅
6 Sparfels: Fast Reconstruction from Sparse Unposed Imagery 提出Sparfels，利用3D基础模型快速重建稀疏无姿态图像 gaussian splatting splatting foundation model
7 Unaligned RGB Guided Hyperspectral Image Super-Resolution with Spatial-Spectral Concordance 提出空间-光谱一致性超分框架，解决非对齐RGB引导的高光谱图像超分辨率重建问题 optical flow HSI feature matching
8 HandOcc: NeRF-based Hand Rendering with Occupancy Networks 提出HandOcc以解决手部渲染中的网格依赖问题 NeRF

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
9 Visual Dominance and Emerging Multimodal Approaches in Distracted Driving Detection: A Review of Machine Learning Techniques 综述：基于机器学习的分心驾驶检测中视觉主导与新兴多模态方法研究 multimodal
10 RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video RTV-Bench：提出实时视频多模态大语言模型评测基准，用于连续感知、理解和推理 large language model multimodal
11 A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models 针对大视觉语言模型中的视觉对象幻觉问题，提出综合分析与缓解方法 large language model multimodal
12 R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation 提出R-Bench：面向LLM/MLLM复杂推理评估的研究生级别多学科基准 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
13 Lifelong Whole Slide Image Analysis: Online Vision-Language Adaptation and Past-to-Present Gradient Distillation 提出ADaFGrad，用于WSI终身学习，提升在线视觉-语言适应能力和梯度蒸馏效果。 distillation foundation model
14 Segment Any RGB-Thermal Model with Language-aided Distillation 提出SARTM框架，通过语言引导的知识蒸馏定制SAM模型用于RGB-T语义分割 distillation scene understanding

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 MLLM-Enhanced Face Forgery Detection: A Vision-Language Fusion Solution 提出VLF-FFD：一种MLLM增强的视觉-语言融合人脸伪造检测方案 manipulation large language model multimodal

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
16 Focus What Matters: Matchability-Based Reweighting for Local Feature Matching 提出基于匹配性的局部特征匹配重加权方法，提升半稠密匹配精度。 feature matching

⬅️ 返回 cs.CV 首页 · 🏠 返回主页