Search Results for author: Sören Pirk

Found 19 papers, 1 papers with code

LRM-Zero: Training Large Reconstruction Models with Synthesized Data

1 code implementation13 Jun 2024 Desai Xie, Sai Bi, Zhixin Shu, Kai Zhang, Zexiang Xu, Yi Zhou, Sören Pirk, Arie Kaufman, Xin Sun, Hao Tan

We demonstrate that our LRM-Zero, trained with our fully synthesized Zeroverse, can achieve high visual quality in the reconstruction of real-world objects, competitive with models trained on Objaverse.

3D Reconstruction

One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns

no code implementations25 Apr 2024 Arman Maesumi, Dylan Hu, Krishi Saripalli, Vladimir G. Kim, Matthew Fisher, Sören Pirk, Daniel Ritchie

Procedural noise is a fundamental component of computer graphics pipelines, offering a flexible way to generate textures that exhibit "natural" random variation.

Data Augmentation Denoising

LAESI: Leaf Area Estimation with Synthetic Imagery

no code implementations31 Mar 2024 Jacek Kałużny, Yannik Schreckenberg, Karol Cyganik, Peter Annighöfer, Sören Pirk, Dominik L. Michels, Mikolaj Cieslak, Farhah Assaad-Gerbert, Bedrich Benes, Wojciech Pałubicki

We introduce LAESI, a Synthetic Leaf Dataset of 100, 000 synthetic leaf images on millimeter paper, each with semantic masks and surface area labels.

Semantic Segmentation

Generating Diverse Agricultural Data for Vision-Based Farming Applications

no code implementations27 Mar 2024 Mikolaj Cieslak, Umabharathi Govindarajan, Alejandro Garcia, Anuradha Chandrashekar, Torsten Hädrich, Aleksander Mendoza-Drosik, Dominik L. Michels, Sören Pirk, Chia-Chun Fu, Wojciech Pałubicki

The integration of real-world textures and environmental factors into the procedural generation process enhances the photorealism and applicability of the synthetic data.

Semantic Segmentation

A Lennard-Jones Layer for Distribution Normalization

no code implementations5 Feb 2024 Mulun Na, Jonathan Klein, Biao Zhang, Wojtek Pałubicki, Sören Pirk, Dominik L. Michels

We introduce the Lennard-Jones layer (LJL) for the equalization of the density of 2D and 3D point clouds through systematically rearranging points without destroying their overall structure (distribution normalization).

Denoising Point Cloud Generation

Gazebo Plants: Simulating Plant-Robot Interaction with Cosserat Rods

no code implementations4 Feb 2024 Junchen Deng, Samhita Marri, Jonathan Klein, Wojtek Pałubicki, Sören Pirk, Girish Chowdhary, Dominik L. Michels

Robotic harvesting has the potential to positively impact agricultural productivity, reduce costs, improve food quality, enhance sustainability, and to address labor shortage.

Image Segmentation object-detection +2

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

no code implementations CVPR 2024 Desai Xie, Jiahao Li, Hao Tan, Xin Sun, Zhixin Shu, Yi Zhou, Sai Bi, Sören Pirk, Arie E. Kaufman

To this end, we introduce Carve3D, an improved RLFT algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, to enhance the consistency of multi-view diffusion models.

Language Modelling Large Language Model +1

DeepTree: Modeling Trees with Situated Latents

no code implementations9 May 2023 Xiaochen Zhou, Bosheng Li, Bedrich Benes, Songlin Fei, Sören Pirk

We use a neural network pipeline to train a situated latent space that allows us to locally predict branch growth only based on a single node in the branch graph of a tree model.

Instance Segmentation with Cross-Modal Consistency

no code implementations14 Oct 2022 Alex Zihao Zhu, Vincent Casser, Reza Mahjourian, Henrik Kretzschmar, Sören Pirk

We demonstrate that this formulation encourages the models to learn embeddings that are invariant to viewpoint variations and consistent across sensor modalities.

Autonomous Driving Contrastive Learning +4

Gesture2Path: Imitation Learning for Gesture-aware Navigation

no code implementations19 Sep 2022 Catie Cuan, Edward Lee, Emre Fisher, Anthony Francis, Leila Takayama, Tingnan Zhang, Alexander Toshev, Sören Pirk

Our experiments indicate that our method is able to successfully interpret complex human gestures and to use them as a signal to generate socially compliant trajectories for navigation tasks.

Imitation Learning Model Predictive Control +2

Procedural Urban Forestry

no code implementations12 Aug 2020 Till Niese, Sören Pirk, Matthias Albrecht, Bedrich Benes, Oliver Deussen

The placement of vegetation plays a central role in the realism of virtual scenes.

Domain Adaptation with Morphologic Segmentation

no code implementations16 Jun 2020 Jonathan Klein, Sören Pirk, Dominik L. Michels

We present a novel domain adaptation framework that uses morphologic segmentation to translate images from arbitrary input domains (real and synthetic) into a uniform output domain.

Domain Adaptation Image-to-Image Translation +1

Modeling Long-horizon Tasks as Sequential Interaction Landscapes

no code implementations8 Jun 2020 Sören Pirk, Karol Hausman, Alexander Toshev, Mohi Khansari

We show that complex plans can be carried out when executing the robotic task and the robot can interactively adapt to changes in the environment and recover from failure cases.

Robot Manipulation

Accurately Solving Physical Systems with Graph Learning

no code implementations6 Jun 2020 Han Shao, Tassilo Kugelstadt, Torsten Hädrich, Wojciech Pałubicki, Jan Bender, Sören Pirk, Dominik L. Michels

In this contribution, we introduce a novel method to accelerate iterative solvers for physical systems with graph networks (GNs) by predicting the initial guesses to reduce the number of iterations.

Graph Learning

Taskology: Utilizing Task Relations at Scale

no code implementations CVPR 2021 Yao Lu, Sören Pirk, Jan Dlabal, Anthony Brohan, Ankita Pasad, Zhao Chen, Vincent Casser, Anelia Angelova, Ariel Gordon

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e. g. object classification, detection, scene segmentation, depth estimation, etc.

Depth Estimation Motion Estimation +4

Data-Efficient Learning for Sim-to-Real Robotic Grasping using Deep Point Cloud Prediction Networks

no code implementations21 Jun 2019 Xinchen Yan, Mohi Khansari, Jasmine Hsu, Yuanzheng Gong, Yunfei Bai, Sören Pirk, Honglak Lee

Training a deep network policy for robot manipulation is notoriously costly and time consuming as it depends on collecting a significant amount of real world data.

3D Shape Representation Object +2

Online Object Representations with Contrastive Learning

no code implementations10 Jun 2019 Sören Pirk, Mohi Khansari, Yunfei Bai, Corey Lynch, Pierre Sermanet

We propose a self-supervised approach for learning representations of objects from monocular videos and demonstrate it is particularly useful in situated settings such as robotics.

Contrastive Learning Object

Understanding and Exploiting Object Interaction Landscapes

no code implementations27 Sep 2016 Sören Pirk, Vojtech Krs, Kaimo Hu, Suren Deepak Rajasekaran, Hao Kang, Bedrich Benes, Yusuke Yoshiyasu, Leonidas J. Guibas

We introduce a new general representation for proximal interactions among physical objects that is agnostic to the type of objects or interaction involved.


Cannot find the paper you are looking for? You can Submit a new open access paper.