SuperPrimitive: Scene Reconstruction at a Primitive Level

no code implementations • 10 Dec 2023 • Kirill Mazur, Gwangbin Bae, Andrew J. Davison

We address this issue with a new image representation which we call a SuperPrimitive.

3D Reconstruction Depth Completion +1

Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding

no code implementations • 6 Oct 2022 • Kirill Mazur, Edgar Sucar, Andrew J. Davison

General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped.

Scene Understanding

Point-Based Modeling of Human Clothing

1 code implementation • ICCV 2021 • Ilya Zakharkin, Kirill Mazur, Artur Grigorev, Victor Lempitsky

We propose a new approach to human clothing modeling based on point clouds.

Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks

no code implementations • ICCV 2021 • Kirill Mazur, Victor Lempitsky

We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks.

Point Cloud Classification Point cloud reconstruction +2