SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.14158 · CVPR · 2023

BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Jan Kautz, Dieter Fox, Jonathan Tremblay, Stephen Tyree, Thomas Müller, Valts Blukis, Alex Evans, Bowen Wen, Stan Nvidia

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1. Given a monocular RGBD sequence and 2D object mask (in the first frame only), our method performs causal 6-DoF tracking and 3D reconstruction of an unknown object. Without any prior knowledge of the object or interaction agent, our method generalizes well, handling flat and untextured surfaces, specular highlights, thin structures, severe occlusion, and a variety of interaction agents (human hand / body / robotic arm). The visualized meshes are directly output by the method.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.14158")
get_code_for_paper("2303.14158")
have("2303.14158")

Connect an agent — have() is free.