cs.CV（2025-12-06）

📊 共 11 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱三：空间感知 (Perception & SLAM) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱四：生成式动作 (Generative Motion) (1 🔗1)

🔬 支柱三：空间感知 (Perception & SLAM) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting	TriaGS：通过可微三角测量引导几何一致性的3D高斯溅射	3D gaussian splatting gaussian splatting novel view synthesis
2	GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation	GNC-Pose：结合几何感知的GNC-PnP方法，实现精确的6D位姿估计	pose estimation feature matching
3	AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars	AGORA：提出基于对抗生成网络的实时可控3D高斯头部头像	3D gaussian splatting 3DGS gaussian splatting	✅
4	Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation	提出基于时空特性的事件相机人体姿态估计方法，提升效率与精度	point cloud pose estimation
5	HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos	提出HuPrior3R，融合人体先验知识，提升单目视频3D动态重建效果	depth estimation monocular depth SMPL
6	When Gender is Hard to See: Multi-Attribute Support for Long-Range Recognition	提出双路径Transformer框架，利用CLIP解决远距离图像性别识别难题	localization
7	RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension	提出RefBench-PRO基准，用于评估多模态大模型在指代表达理解中的感知和推理能力。	localization

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
8	VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning	提出VG-Refiner，通过Agent强化学习优化工具反馈，提升指代 grounding 推理能力	reinforcement learning
9	S2WMamba: A Spectral-Spatial Wavelet Mamba for Pansharpening	提出S2WMamba，通过谱-空域小波变换和Mamba模块实现高效遥感图像融合	Mamba	✅
10	ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models	ReCAD：利用强化学习增强的参数化CAD模型生成，结合视觉-语言模型	reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	DragMesh: Interactive 3D Generation Made Easy	DragMesh：提出解耦运动生成框架，实现实时交互式3D模型可动性生成。	motion generation	✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页