cs.CV（2024-07-15）
📊 共 6 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) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion | 提出NOVIC，通过CLIP反演实现无约束开放词汇图像分类的零样本迁移。 | open-vocabulary open vocabulary zero-shot transfer | ||
| 2 | Evaluating geometric accuracy of NeRF reconstructions compared to SLAM method | 评估NeRF重建几何精度，对比SLAM方法在PVC圆柱体直径估计中的表现 | NeRF neural radiance field scene reconstruction | ||
| 3 | Benchmarking Vision Language Models for Cultural Understanding | 提出CulturalVQA基准，评估视觉语言模型对多元文化的理解能力。 | scene understanding foundation model multimodal | ||
| 4 | FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation | FRI-Net：提出基于房间隐式表达的楼层平面图重建方法 | implicit representation | ||
| 5 | Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation | 提出基于运动先验对比最大化的密集连续时间运动估计方法 | optical flow | ✅ | |
| 6 | No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations | FUNGI：利用自监督梯度提升冻结Transformer表征，无需训练。 | scene understanding |