cs.CV（2025-08-07）
📊 共 4 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1)
支柱二：RL算法与架构 (RL & Architecture) (1)
支柱九：具身大模型 (Embodied Foundation Models) (1)
🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion | 提出深度基础模型以解决分布外深度补全问题 | depth estimation monocular depth foundation model | ✅ | |
| 2 | UGOD: Uncertainty-Guided Differentiable Opacity and Soft Dropout for Enhanced Sparse-View 3DGS | 提出不确定性引导的可微透明度与软丢弃以提升稀疏视图3DGS | 3D gaussian splatting 3DGS gaussian splatting |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 3 | Multimodal Causal-Driven Representation Learning for Generalizable Medical Image Segmentation | 提出多模态因果驱动表示学习以解决医学图像分割的领域泛化问题 | representation learning multimodal |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Surformer v1: Transformer-Based Surface Classification Using Tactile and Vision Features | 提出Surformer v1以解决表面材料识别问题 | multimodal |