Peking University, 2025 Fall

<aside> 📎

Final Project

</aside>

Important Dates

Overview

The Course Project is an opportunity for you to apply what you have learned in class to a problem of your interest. Potential projects usually fall into these two tracks:

• Reconstructing semantics from images. Image classification, object detection, semantic segmentation, image generation, etc.
• Reconstructing 3D from images. You can choose to implement traditional algorithms, deep learning algorithms, or a combination of both to achieve the goal, such as NeRF (Neural Radiance Field), SLAM, Stereo, etc.

We provide some topics in in the following text, you can choose one from them. You can also explore other topics on the above two tracks, instead of choosing those we provide. We encourage in-group discussion and finishing tasks independently within the group, but if you need necessary help, feel free to contact us. Hope you enjoy the final project!

To inspire ideas, you might also look at recent deep learning publications from top-tier conferences, as well as other resources below.

• CVPR: IEEE Conference on Computer Vision and Pattern Recognition
• ICCV: International Conference on Computer Vision
• ECCV: European Conference on Computer Vision
• NIPS: Neural Information Processing Systems
• ICLR: International Conference on Learning Representations
• Kaggle challenges: An online machine learning competition website.

You might also gain inspiration by taking a look at some past Projects of Stanford cs231n & cs229.

• Stanford University CS231n