cs.CV（2024-02-06）

📊 共 16 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱四：生成式动作 (Generative Motion) (1) 支柱一：机器人控制 (Robot Control) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models	提出SHIELD基准以评估多模态大语言模型在面部欺诈检测中的表现	large language model multimodal chain-of-thought
2	Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap	提出多模态无监督领域泛化方法以解决标签空间不一致问题	multimodal	✅
3	Multimodal Rationales for Explainable Visual Question Answering	提出MRVQA以解决视觉问答中的可解释性问题	multimodal	✅
4	EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters	提出EVA-CLIP-18B以提升多模态模型性能	foundation model multimodal
5	The Instinctive Bias: Spurious Images lead to Illusion in MLLMs	提出CorrelationQA以解决多模态大语言模型的视觉幻觉问题	large language model	✅

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

#	题目	一句话要点	标签	🔗	⭐
6	MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstruction	提出MoD-SLAM以解决无界3D场景重建问题	depth estimation 3D reconstruction NeRF
7	Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos	提出Rig3DGS以解决从单视角视频生成可控3D人像问题	3D gaussian splatting 3DGS gaussian splatting	✅
8	YOLOPoint Joint Keypoint and Object Detection	提出YOLOPoint以实现关键点与物体的联合检测	visual odometry
9	EscherNet: A Generative Model for Scalable View Synthesis	提出EscherNet以解决可扩展视图合成问题	3D reconstruction	✅
10	Energy-based Domain-Adaptive Segmentation with Depth Guidance	提出SMART框架以解决深度引导的无监督领域自适应分割问题	depth estimation

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

#	题目	一句话要点	标签	🔗	⭐
11	Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback	提出基于AI反馈的强化学习方法以优化视频多模态模型	reinforcement learning large language model multimodal
12	Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models	提出弱到强的监督学习方法以提升视觉基础模型性能	distillation large language model foundation model	✅
13	U-shaped Vision Mamba for Single Image Dehazing	提出U-shaped Vision Mamba以解决单幅图像去雾问题	Mamba SSM	✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
14	Bidirectional Autoregressive Diffusion Model for Dance Generation	提出双向自回归扩散模型以解决舞蹈生成问题	motion generation human motion human motion generation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
15	CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning	提出CogCoM以解决视觉语言模型中的推理不足问题	manipulation	✅

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

#	题目	一句话要点	标签	🔗	⭐
16	ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation	提出ConsistI2V以解决图像到视频生成中的视觉一致性问题	spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页