cs.CV（2025-11-04）

📊 共 17 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知 (Perception & SLAM) (14 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱三：空间感知 (Perception & SLAM) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Object-Centric 3D Gaussian Splatting for Strawberry Plant Reconstruction and Phenotyping	提出对象中心3D高斯溅射方法，用于草莓植株重建与表型分析	3D gaussian splatting 3DGS gaussian splatting
2	Monocular absolute depth estimation from endoscopy via domain-invariant feature learning and latent consistency	提出基于特征对齐和潜在一致性的单目内窥镜绝对深度估计方法	depth estimation monocular depth	✅
3	From Propagation to Prediction: Point-level Uncertainty Evaluation of MLS Point Clouds under Limited Ground Truth	提出一种基于学习的MLS点云不确定性评估框架，无需大量真值数据。	point cloud
4	EvtSlowTV -- A Large and Diverse Dataset for Event-Based Depth Estimation	EvtSlowTV：用于事件相机深度估计的大规模多样化数据集	depth estimation
5	Object Detection as an Optional Basis: A Graph Matching Network for Cross-View UAV Localization	提出基于对象检测和图匹配网络的跨视角无人机定位方法，解决异构图像匹配问题。	localization	✅
6	A Novel Grouping-Based Hybrid Color Correction Algorithm for Color Point Clouds	提出一种基于分组的混合颜色校正算法，用于彩色点云的颜色一致性校正。	point cloud	✅
7	Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization	Cycle-Sync：通过增强的循环一致性同步实现稳健的全局相机位姿估计	pose estimation
8	3D Point Cloud Object Detection on Edge Devices for Split Computing	针对边缘设备，提出基于Split Computing的3D点云目标检测方法，降低计算负担。	point cloud
9	Are Euler angles a useful rotation parameterisation for pose estimation with Normalizing Flows?	探索欧拉角在Normalizing Flows姿态估计中的有效性，对比复杂参数化模型。	pose estimation
10	Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Data	提出无监督学习方法以解决工业缺陷检测问题	localization feature matching
11	LiteVoxel: Low-memory Intelligent Thresholding for Efficient Voxel Rasterization	提出LiteVoxel以解决稀疏体素光栅化中的低频内容不足问题	NeRF scene reconstruction
12	PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing	PercHead：提出基于感知的头部模型，用于单图像3D头部重建与编辑	gaussian splatting	✅
13	OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control	提出OLATverse数据集以解决真实世界物体渲染的局限性	novel view synthesis
14	Can Foundation Models Revolutionize Mobile AR Sparse Sensing?	利用Foundation Model革新移动AR稀疏感知，提升几何图像扭曲与3D重建	scene reconstruction

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

#	题目	一句话要点	标签	🔗	⭐
15	Self-Supervised Moving Object Segmentation of Sparse and Noisy Radar Point Clouds	提出一种自监督雷达点云移动物体分割方法，提升稀疏噪声数据的分割性能。	representation learning SLAM point cloud
16	M2S2L: Mamba-based Multi-Scale Spatial-temporal Learning for Video Anomaly Detection	提出基于Mamba的多尺度时空学习框架M2S2L，用于提升视频异常检测的精度和效率。	Mamba

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping	DiffSwap++：利用3D人脸先验的身份保持型人脸交换扩散模型	geometric consistency	✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页