no code implementations • 14 Dec 2023 • Hongsuk Choi, Isaac Kasahara, Selim Engin, Moritz Graule, Nikhil Chavan-Dafle, Volkan Isler
While ControlNet provides control over the geometric form of the instances in the generated image, it lacks the capability to dictate the visual appearance of each instance.
no code implementations • 8 Nov 2023 • Jun-Jee Chao, Selim Engin, Nikhil Chavan-Dafle, Bhoram Lee, Volkan Isler
We study the problem of aligning a video that captures a local portion of an environment to the 2D LiDAR scan of the entire environment.
no code implementations • 21 Jul 2023 • Isaac Kasahara, Shubham Agrawal, Selim Engin, Nikhil Chavan-Dafle, Shuran Song, Volkan Isler
General scene reconstruction refers to the task of estimating the full 3D geometry and texture of a scene containing previously unseen objects.
1 code implementation • 16 May 2023 • Shubham Agrawal, Nikhil Chavan-Dafle, Isaac Kasahara, Selim Engin, Jinwook Huh, Volkan Isler
In this paper, we present a novel method to provide this geometric and semantic information of all objects in the scene as well as feasible grasps on those objects simultaneously.
no code implementations • 28 Sep 2022 • Jun-Jee Chao, Selim Engin, Nicolai Häni, Volkan Isler
This paper proposes an optimization method that retains all possible correspondences for each keypoint when matching a partial point cloud to a complete point cloud.
1 code implementation • NeurIPS 2020 • Nicolai Häni, Selim Engin, Jun-Jee Chao, Volkan Isler
As a result, current approaches typically rely on supervised training with either ground truth 3D models or multiple target images.
no code implementations • 4 Oct 2019 • Selim Engin, Eric Mitchell, Daewon Lee, Volkan Isler, Daniel D. Lee
In contrast to offline methods which require a 3D model of the object as input or online methods which rely on only local measurements, our method uses a neural network which encodes shape information for a large number of objects.
no code implementations • ICLR 2020 • Eric Mitchell, Selim Engin, Volkan Isler, Daniel D. Lee
We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network.