cs.CV（2024-08-17）

📊 共 12 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) (5) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting	Gaussian-DK：利用高斯溅射从不一致的黑暗图像中进行实时视角合成	3D gaussian splatting gaussian splatting splatting
2	Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community	提出LAE-DINO模型，解决遥感图像开放词汇目标检测中的领域泛化难题	open-vocabulary open vocabulary
3	HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Prediction	HybridOcc：NeRF增强的Transformer多相机3D Occupancy预测	NeRF
4	GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking System	GSLAMOT：提出基于轨迹片段和查询图的同步定位、建图与多目标跟踪系统	semantic map multimodal
5	GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation	GoodSAM++：利用SAM弥合领域和容量差距，实现全景语义分割	semantic map

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
6	MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model	提出基于Mamba状态空间模型的多目标跟踪简单基线MambaTrack，解决非线性运动跟踪难题。	Mamba SSM state space model
7	Zero-Shot Object-Centric Representation Learning	提出零样本目标中心表示学习框架，提升模型在未见数据集上的物体发现能力。	representation learning foundation model zero-shot transfer
8	SSNeRF: Sparse View Semi-supervised Neural Radiance Fields with Augmentation	SSNeRF：基于增广的稀疏视角半监督神经辐射场，提升少样本视角下的NeRF重建质量。	teacher-student NeRF neural radiance field
9	DRL-Based Resource Allocation for Motion Blur Resistant Federated Self-Supervised Learning in IoV	提出基于DRL的资源分配方案，用于IoV中抗运动模糊的联邦自监督学习。	reinforcement learning deep reinforcement learning DRL

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Are CLIP features all you need for Universal Synthetic Image Origin Attribution?	利用CLIP特征进行通用合成图像溯源，解决开放集场景下的模型归属问题	foundation model	✅
11	Segment Anything with Multiple Modalities	MM-SAM：扩展SAM以支持多模态数据分割，提升各种传感器下的鲁棒性。	foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Flatten: Video Action Recognition is an Image Classification task	Flatten：将视频动作识别转化为图像分类任务，提升效率与性能	spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页