cs.CV（2024-04-15）

📊 共 39 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (11 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (11 🔗4) 支柱四：生成式动作 (Generative Motion) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (2) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (12 篇)

#题目一句话要点标签🔗⭐
1 3D Gaussian Splatting as Markov Chain Monte Carlo 提出基于MCMC的3D高斯点云渲染方法以提升质量 3D gaussian splatting gaussian splatting splatting
2 DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shading 提出DeferredGS以解决高效渲染与编辑3D场景的问题 gaussian splatting splatting NeRF
3 Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation? 提出ANYU数据集以提升单目深度估计性能 depth estimation monocular depth ✅
4 CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting 提出压缩高斯点云表示以解决3D场景数据体积过大的问题 gaussian splatting splatting
5 VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection 提出VFMM3D以解决单目3D目标检测问题 Depth Anything foundation model
6 Taming Latent Diffusion Model for Neural Radiance Field Inpainting 提出潜在扩散模型以解决NeRF修复中的几何合成问题 3D reconstruction NeRF neural radiance field ✅
7 LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives 提出LiDAR辅助高斯原语框架以解决大型车库建模与渲染问题 3D gaussian splatting 3D reconstruction gaussian splatting
8 ViFu: Multiple 360$^\circ$ Objects Reconstruction with Clean Background via Visible Part Fusion 提出ViFu以解决360°物体重建与干净背景分离问题 neural radiance field TAMP
9 Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video 提出Video2Game以解决高质量虚拟环境构建问题 NeRF neural radiance field
10 kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies 提出kNN-CLIP以解决开放词汇分割中的灾难性遗忘问题 open-vocabulary open vocabulary
11 Table tennis ball spin estimation with an event camera 提出基于事件相机的乒乓球旋转估计方法以解决传统相机不足问题 optical flow
12 FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features 提出FSRT以解决面部重演中的跨人物动态转移问题 optical flow

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
13 Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL 提出结合视觉基础模型与离线强化学习以提升具身视觉跟踪能力 reinforcement learning offline RL offline reinforcement learning
14 Evolving Interpretable Visual Classifiers with Large Language Models 提出一种新方法以解决视觉分类器的可解释性问题 privileged information open-vocabulary open vocabulary
15 FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba 提出FusionMamba以解决多模态图像融合中的特征捕获问题 Mamba state space model multimodal
16 Digging into contrastive learning for robust depth estimation with diffusion models 提出D4RD以解决复杂环境下深度估计不可靠问题 contrastive learning distillation depth estimation ✅
17 HSIDMamba: Exploring Bidirectional State-Space Models for Hyperspectral Denoising 提出HSIDMamba以解决高光谱图像去噪问题 Mamba SSM state space model
18 Fuse after Align: Improving Face-Voice Association Learning via Multimodal Encoder 提出多模态编码器以改善人脸与声音关联学习 contrastive learning multimodal
19 CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders 提出CryoMAE以解决低信噪比下的冷冻电镜颗粒选择问题 masked autoencoder MAE 3D reconstruction
20 EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning 提出EyeFormer以解决个性化扫描路径预测问题 reinforcement learning deep reinforcement learning
21 Cross-Modal Self-Training: Aligning Images and Pointclouds to Learn Classification without Labels 提出Cross-MoST以解决无标签3D分类问题 representation learning open-vocabulary open vocabulary
22 WB LUTs: Contrastive Learning for White Balancing Lookup Tables 提出WB LUTs以解决自动白平衡问题 contrastive learning ✅
23 FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining 提出FreqMamba以解决图像雨滴去除问题 Mamba

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
24 AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception 提出AesExpert以解决图像美学感知的多模态挑战 large language model foundation model multimodal ✅
25 TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding 提出TextCoT框架以解决文本丰富图像理解问题 multimodal chain-of-thought ✅
26 AIGeN: An Adversarial Approach for Instruction Generation in VLN 提出AIGeN以解决视觉语言导航中的指令生成问题 VLN
27 PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI 提出PhyScene以解决交互式3D场景生成的物理可交互性问题 embodied AI
28 MMInA: Benchmarking Multihop Multimodal Internet Agents 提出MMInA基准以评估多跳多模态互联网代理的能力 multimodal
29 How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Model 基于基础模型的医学图像分割算法优化研究 foundation model ✅
30 Bridging Vision and Language Spaces with Assignment Prediction 提出VLAP以实现视觉与语言空间的有效融合 large language model multimodal
31 HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing 提出HQ-Edit以解决高质量指令基础图像编辑数据集构建问题 foundation model ✅
32 Harnessing GPT-4V(ision) for Insurance: A Preliminary Exploration 利用GPT-4V解决保险领域的多模态任务挑战 multimodal
33 Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection 提出ALFA以解决视觉异常检测中的语义歧义问题 large language model
34 UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark 提出UNIAA框架以解决图像美学评估的单一数据源问题 large language model

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
35 in2IN: Leveraging individual Information to Generate Human INteractions 提出in2IN以解决人际运动交互生成的多样性问题 motion generation human motion human motion generation
36 Magic Clothing: Controllable Garment-Driven Image Synthesis 提出Magic Clothing以解决服装驱动图像合成问题 classifier-free guidance ✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
37 Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment 提出视频到运动生成器以解决单目视频中的3D人类运动重建问题 video-to-motion human motion
38 XoFTR: Cross-modal Feature Matching Transformer 提出XoFTR以解决可见光与热红外图像匹配问题 feature matching

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
39 HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision 提出HOI-Ref任务以解决自我视角下手物交互识别问题 HOI egocentric egocentric vision

⬅️ 返回 cs.CV 首页 · 🏠 返回主页