cs.CV（2023-10-12）

📊 共 21 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (6 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	4D Gaussian Splatting for Real-Time Dynamic Scene Rendering	提出4D高斯点云渲染方法以解决动态场景实时渲染问题	gaussian splatting splatting TAMP	✅
2	EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenes	提出EC-Depth以解决自监督单目深度估计在复杂场景中的一致性问题	depth estimation monocular depth
3	PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm	提出PonderV2以解决3D基础模型预训练的挑战	3D reconstruction foundation model	✅
4	RT-SRTS: Angle-Agnostic Real-Time Simultaneous 3D Reconstruction and Tumor Segmentation from Single X-Ray Projection	提出RT-SRTS以解决实时肿瘤分割与三维重建问题	3D reconstruction	✅
5	Consistent123: Improve Consistency for One Image to 3D Object Synthesis	提出Consistent123以解决3D对象合成中的视图一致性问题	3D reconstruction classifier-free guidance
6	Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction	提出隐式形状与外观先验以解决少样本全头重建问题	3D reconstruction

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

#	题目	一句话要点	标签	🔗	⭐
7	Multimodal Large Language Model for Visual Navigation	提出多模态大语言模型以解决视觉导航问题	behavior cloning large language model multimodal
8	GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models	提出GaussianDreamer以解决3D资产生成的速度与质量问题	dreamer 3D gaussian splatting gaussian splatting
9	Multimodal Variational Auto-encoder based Audio-Visual Segmentation	提出显式条件多模态变分自编码器解决音视频分割问题	representation learning multimodal
10	Aligning Data Selection with Performance: Performance-driven Reinforcement Learning for Active Learning in Object Detection	提出MGRAL以解决目标检测中的主动学习数据选择问题	reinforcement learning
11	Hyp-UML: Hyperbolic Image Retrieval with Uncertainty-aware Metric Learning	提出Hyp-UML以解决图像检索中的不确定性问题	representation learning contrastive learning

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Octopus: Embodied Vision-Language Programmer from Environmental Feedback	提出Octopus以解决高层规划与实际操作之间的鸿沟问题	manipulation reinforcement learning embodied AI
13	DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception	提出DUSA以解决V2X协作感知中的Sim2Real适应问题	sim2real
14	Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models	提出视觉数据类型识别以解决视觉语言模型的盲点问题	manipulation	✅

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

#	题目	一句话要点	标签	🔗	⭐
15	Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models	提出广义逻辑调整方法以消除基础模型中的标签偏差	foundation model zero-shot transfer	✅
16	STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment	提出STELLA以解决音视频持续学习中的时空关联问题	multimodal

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
17	A Deep Learning Framework for Spatiotemporal Ultrasound Localization Microscopy	提出深度学习框架以解决超声定位显微镜中的微血管重建问题	spatiotemporal
18	Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes	提出Im4D以解决动态场景中的视图合成问题	spatiotemporal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	OmniControl: Control Any Joint at Any Time for Human Motion Generation	提出OmniControl以解决人类动作生成中的关节控制问题	motion generation OmniControl human motion

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

#	题目	一句话要点	标签	🔗	⭐
20	Mapping Memes to Words for Multimodal Hateful Meme Classification	提出ISSUES以解决多模态仇恨表情包分类问题	HuMoR multimodal	✅

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

#	题目	一句话要点	标签	🔗	⭐
21	DiscoMatch: Fast Discrete Optimisation for Geometrically Consistent 3D Shape Matching	提出DiscoMatch以解决3D形状匹配中的几何一致性问题	geometric consistency

⬅️ 返回 cs.CV 首页 · 🏠 返回主页