CVPR 2024 论文和代码速递！ 2024.4.17

推荐

微信交流群现已有2000+从业人员交流群，欢迎进群交流学习，微信：nvshenj125

B站最新成果demo分享地址：https://space.bilibili.com/288489574

顶会工作整理Github repo：https://github.com/DWCTOD/CVPR2023-Papers-with-Code-Demo

工作整理

CVPR 2024

Updated on : 17

total number : 10

Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences

• 论文/Paper: http://arxiv.org/abs/2404.10603

• 代码/Code: None

The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement

• 论文/Paper: http://arxiv.org/abs/2404.10438

• 代码/Code: https://github.com/ga1i13o/mcloc_poseref

Adversarial Identity Injection for Semantic Face Image Synthesis

• 论文/Paper: http://arxiv.org/abs/2404.10408

• 代码/Code: None

Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation

• 论文/Paper: http://arxiv.org/abs/2404.10322

• 代码/Code: https://github.com/Matt-Su/DR-Adapter.

Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology

• 论文/Paper: http://arxiv.org/abs/2404.10242

• 代码/Code: None

MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints

• 论文/Paper: http://arxiv.org/abs/2404.10227

• 代码/Code: None

Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering

• 论文/Paper: http://arxiv.org/abs/2404.10193

• 代码/Code: None

Salient Object-Aware Background Generation using Text-Guided Diffusion Models

• 论文/Paper: http://arxiv.org/abs/2404.10157

• 代码/Code: None

Cross-Modal Self-Training: Aligning Images and Pointclouds to Learn Classification without Labels

• 论文/Paper: http://arxiv.org/abs/2404.10146

• 代码/Code: https://github.com/theamaya/crossmost

Epistemic Uncertainty Quantification For Pre-trained Neural Network

• 论文/Paper: http://arxiv.org/abs/2404.10124

• 代码/Code: None