cs.CV（2024-01-11）

📊 共 18 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (10 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (10 篇)

#题目一句话要点标签🔗⭐
1 Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery 提出Surgical-DINO以解决内窥镜手术中的深度估计问题 depth estimation 3D reconstruction foundation model ✅
2 GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content Creation 提出GO-NeRF以解决虚拟环境中3D对象生成与集成问题 NeRF neural radiance field
3 TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Rendering 提出TRIPS以解决实时辐射场渲染中的模糊和不稳定问题 3D gaussian splatting gaussian splatting splatting ✅
4 YOIO: You Only Iterate Once by mining and fusing multiple necessary global information in the optical flow estimation 提出YOIO框架以解决光流估计中的遮挡问题 optical flow spatiotemporal
5 TriNeRFLet: A Wavelet Based Triplane NeRF Representation 提出TriNeRFLet以解决三维恢复质量不足问题 NeRF neural radiance field
6 A Study on Self-Supervised Pretraining for Vision Problems in Gastrointestinal Endoscopy 研究自监督预训练以提升胃肠内窥镜视觉任务性能 depth estimation monocular depth
7 Gaussian Shadow Casting for Neural Characters 提出高斯阴影投射模型以解决神经角色阴影缺失问题 gaussian splatting splatting
8 Fast High Dynamic Range Radiance Fields for Dynamic Scenes 提出HDR-HexPlane以解决动态场景中的高动态范围图像合成问题 NeRF ✅
9 RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks 提出RAVEN以高效生成长视频并解决时空依赖问题 optical flow
10 Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation 提出紧凑分段3D高斯模型以解决零样本神经场景分割问题 scene understanding ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
11 Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs 提出Mixture of Features以解决多模态LLMs视觉短板问题 representation learning large language model multimodal
12 Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection 提出自交叉三元组相关性方法以提升人-物交互检测精度 distillation scene understanding human-object interaction
13 HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition 提出HiCMAE以解决音视频情感识别中的数据稀缺问题 representation learning masked autoencoder contrastive learning ✅
14 Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairing 提出高效组合正对配对方法以提升对比学习效果 representation learning contrastive learning
15 Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition 提出分层增强与蒸馏方法以解决增量音视频识别问题 distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
16 Video Anomaly Detection and Explanation via Large Language Models 提出基于大语言模型的视频异常检测方法以解决阈值复杂性问题 large language model
17 GroundingGPT:Language Enhanced Multi-modal Grounding Model 提出GroundingGPT以解决多模态细粒度理解问题 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations 通过解耦虚假相关性与增强潜在相关性提升模型泛化能力 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页