cs.CV（2026-09-09）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (6) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
1 RouteBridge: Reliability-Routed Bidirectional Distillation Between Neural Radiance Fields and 3D Gaussian Splatting 提出RouteBridge以解决NeRF与3DGS间的蒸馏问题 distillation 3D gaussian splatting 3DGS
2 Arti-JEPA: Adapting Video World Model to Real-Time MRI of the Vocal Tract for Speech-Production Analysis 提出Arti-JEPA以解决实时MRI语音生产分析问题 world model world models JEPA
3 Decoupled Self-Forcing Distillation for Streaming Talking Head Generation 提出解耦自强蒸馏方法以提升流媒体人头生成质量 distillation motion latent motion representation
4 Programmable World Model 提出可编程世界模型以解决持久状态管理问题 world model world models spatiotemporal
5 Multimodal Emotion Recognition in Conversations via Class-Wise Adaptive Modality Fusion and Affective Geometry 提出多模态情感识别方法以解决对话中的情感动态问题 distillation multimodal
6 Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs 提出VIP-Router以解决视觉令牌剪枝中的适应性问题 VIP large language model multimodal

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

#题目一句话要点标签🔗⭐
7 Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval 提出基于基础模型的高效训练无关视频检索方法 foundation model multimodal ✅
8 BrainTaskonomy: Learning How to Pretrain and What to Transfer in fMRI Foundation Models 提出BrainTaskonomy以优化fMRI预训练和任务迁移 foundation model
9 AVSRBench: A Multi-Condition AVSR Benchmark 提出AVSRBench以解决多条件下的AVSR泛化问题 multimodal
10 Geometry Without Coordinates: LiDAR Diffusion as a 3D Feature Bridge 提出基于LiDAR的扩散模型以解决3D特征提取问题 foundation model
11 LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial Scenarios 提出LogiScope-VQA以解决工业场景中的物流危险识别问题 multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
12 LinearMask-GS: Stable-Mask Importance Pruning for Compact 3D Gaussian Splatting 提出LinearMask-GS以解决3D高斯点云冗余问题 3D gaussian splatting 3DGS gaussian splatting
13 Shape-guided Gaussian Splatting for Sparse-View X-ray 3D Reconstruction 提出形状引导的高斯点云方法以解决稀视角X射线3D重建问题 3D gaussian splatting 3D reconstruction gaussian splatting ✅
14 Vague2Detect: Handling Ambiguous Prompts in Knowledge-Based Open-World Detection 提出Vague2Detect以解决模糊提示在开放世界检测中的问题 open-vocabulary open vocabulary large language model
15 Guiding Image-to-3D Generation with Test-Time Partial Observations 提出无训练框架以利用测试时部分几何观测指导图像到3D生成 sam 3D SAM 3D

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
16 Isotropic Embedding Perturbations for Robust Vision Language Encoders 提出Aether方法以解决多模态模型数据增强不足问题 manipulation multimodal
17 PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving 提出PACE框架以优化对话服务中的感知延迟问题 humanoid humanoid robot

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
18 3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimation 提出语言对齐运动表示以解决UPDRS步态严重性估计问题 SMPL human motion motion representation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
19 SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination 提出SceneHI框架以解决高分辨率3D纹理合成问题 physically plausible

⬅️ 返回 cs.CV 首页 · 🏠 返回主页