cs.CV（2024-03-25）

📊 共 30 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) (11 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (8 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (11 篇)

#题目一句话要点标签🔗⭐
1 Spike-NeRF: Neural Radiance Field Based On Spike Camera 提出Spike-NeRF以解决高频脉冲数据的3D重建问题 depth estimation 3D reconstruction NeRF
2 GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction 提出GSDF以解决3D场景重建与渲染质量不足问题 3D gaussian splatting 3DGS gaussian splatting
3 Is Your LiDAR Placement Optimized for 3D Scene Understanding? 提出Place3D以优化LiDAR布局解决3D场景理解问题 scene understanding occupancy grid
4 Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion 提出Elite360D以解决360深度估计中的计算成本与局部感受野问题 depth estimation 3D reconstruction
5 DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion 提出DreamPolisher以解决文本到3D生成中的视图一致性问题 gaussian splatting splatting geometric consistency
6 Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding 提出Calib3D以解决3D场景理解模型的不确定性问题 scene understanding
7 ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimation 提出ASDF以解决组装状态检测中的6D姿态估计问题 6D pose estimation
8 DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding 提出DOCTR以解决点云场景理解中的多任务协同问题 scene understanding ✅
9 CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs 提出CVT-xRF以解决稀疏输入下NeRF性能下降问题 NeRF neural radiance field
10 Open-Set Recognition in the Age of Vision-Language Models 提出开放集识别新基准以解决视觉语言模型的局限性 open-vocabulary open vocabulary
11 AI-Generated Video Detection via Spatio-Temporal Anomaly Learning 提出AIGVDet以解决AI生成视频检测问题 optical flow ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
12 Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning 提出Visual CoT以解决多模态语言模型的推理与可解释性问题 large language model chain-of-thought
13 Understanding Long Videos with Multimodal Language Models 提出多模态视频理解框架以提升长视频理解能力 large language model multimodal ✅
14 DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving 提出DriveCoT以解决端到端驾驶系统的可解释性与可控性问题 chain-of-thought
15 SegICL: A Multimodal In-context Learning Framework for Enhanced Segmentation in Medical Imaging 提出SegICL框架以解决医疗影像OOD分割问题 multimodal
16 Data-Efficient 3D Visual Grounding via Order-Aware Referring 提出Vigor框架以解决3D视觉定位的数据效率问题 visual grounding ✅
17 PathoTune: Adapting Visual Foundation Model to Pathological Specialists 提出PathoTune以解决病理图像任务适应性问题 foundation model ✅
18 Dia-LLaMA: Towards Large Language Model-driven CT Report Generation 提出Dia-LLaMA以解决CT报告生成中的偏差与信息丢失问题 large language model
19 Elysium: Exploring Object-level Perception in Videos via MLLM 提出ElysiumTrack-1M以解决视频对象感知问题 large language model ✅

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

#题目一句话要点标签🔗⭐
20 VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting 提出VMRNN以解决时空预测中的信息建模挑战 Mamba spatiotemporal ✅
21 CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification 提出CMViM以解决3D多模态阿尔茨海默病分类问题 Mamba representation learning contrastive learning
22 DreamLIP: Language-Image Pre-training with Long Captions 提出DreamLIP以解决长文本描述图像的不足问题 contrastive learning large language model ✅
23 From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and Knowledge Distillation 提出基于互提示学习和知识蒸馏的高效RGB-T跟踪方法 distillation
24 VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation 提出VP3D以解决文本到3D生成中的视觉一致性问题 distillation NeRF

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
25 Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text 提出Make-It-Vivid以解决卡通角色纹理生成问题 biped
26 V2X-PC: Vehicle-to-everything Collaborative Perception via Point Cluster 提出V2X-PC以解决车辆协同感知中的信息损失问题 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
27 Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects 提出HANDS23挑战以解决自我视角下手部与物体交互的3D重建问题 motion generation egocentric

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
28 An Intermediate Fusion ViT Enables Efficient Text-Image Alignment in Diffusion Models 提出中间融合ViT以提高扩散模型中的文本-图像对齐效率 spatial relationship multimodal

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

#题目一句话要点标签🔗⭐
29 Multi-attention Associate Prediction Network for Visual Tracking 提出多注意力关联预测网络以解决视觉跟踪中的决策不一致问题 feature matching

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

#题目一句话要点标签🔗⭐
30 RSTAR4D: Rotational Streak Artifact Reduction in 4D CBCT using a Separable 4D CNN 提出RSTAR4D-Net以解决4D CBCT中的旋转条纹伪影问题 spatiotemporal ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页