cs.CV（2025-01-11）
📊 共 6 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱二：RL算法与架构 (RL & Architecture) (3)
支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1)
支柱九：具身大模型 (Embodied Foundation Models) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References | 提出NVS-SQA，用于神经渲染场景的无参考自监督质量评估 | representation learning 3D gaussian splatting gaussian splatting | ||
| 2 | Natural Language Supervision for Low-light Image Enhancement | 提出基于自然语言监督的低光图像增强方法NaLSuper，实现视觉和文本特征对齐。 | representation learning multimodal | ||
| 3 | FocusDD: Real-World Scene Infusion for Robust Dataset Distillation | FocusDD：通过真实场景融合实现鲁棒数据集蒸馏，提升小样本训练性能 | distillation |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis | MapGS：利用新视角合成实现可泛化的在线地图构建预训练与数据增强 | gaussian splatting splatting | ✅ | |
| 5 | SP-SLAM: Neural Real-Time Dense SLAM With Scene Priors | SP-SLAM：利用场景先验的神经实时稠密SLAM | implicit representation |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs | SVE-Math：通过几何感知增强视觉数学多模态大语言模型 | large language model multimodal visual grounding |