Enhancing Point Clouds for Better 3D Detection

Student: Aleksandr Dadukin

Supervisor: Ilya Makarov

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Master of Computer Vision (Master)

Final Grade: 10

Year of Graduation: 2024

The work addresses essential challenges that exist in almost every 3D object detection set up: occlusion and sparsity. Existing implementations typically tend to depend on inventing specific architectures, thereby restricting their applicability. To the best of our knowledge, this research is the first to offer a versatile plug-and-play framework called X-Ray Distillation with Object-Complete frames which is possible to integrate to any existing pipeline. The framework reconstructs complete (also referred as augmented) point clouds by leveraging available temporal information. The method surpasses state-of-the-art results in supervised and semi-supervised settings.

Full text (added May 15, 2024)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses