Search Results for author: Leonidas J. Guibas

Found 70 papers, 44 papers with code

Learning a Diffusion Prior for NeRFs

no code implementations27 Apr 2023 Guandao Yang, Abhijit Kundu, Leonidas J. Guibas, Jonathan T. Barron, Ben Poole

Neural Radiance Fields (NeRFs) have emerged as a powerful neural 3D representation for objects and scenes derived from 2D data.

Physics-informed PointNet: On how many irregular geometries can it solve an inverse problem simultaneously? Application to linear elasticity

1 code implementation22 Mar 2023 Ali Kashefi, Leonidas J. Guibas, Tapan Mukerji

In this article, we demonstrate that PIPN predicts the solution of desired partial differential equations over a few hundred domains simultaneously, while it only uses sparse labeled data.

Weakly-supervised Learning

CurveCloudNet: Processing Point Clouds with 1D Structure

no code implementations21 Mar 2023 Colton Stearns, Jiateng Liu, Davis Rempe, Despoina Paschalidou, Jeong Joon Park, Sebastien Mascha, Leonidas J. Guibas

Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene, resulting in a point cloud with notable 1D curve-like structures.

SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry

no code implementations16 Feb 2023 Lin Gao, Jia-Mu Sun, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Jie Yang

We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level.

Scene Generation

Equivalence Between SE(3) Equivariant Networks via Steerable Kernels and Group Convolution

no code implementations29 Nov 2022 Adrien Poulenard, Maks Ovsjanikov, Leonidas J. Guibas

Most approaches for equivariance under the Euclidean group $\mathrm{SE}(3)$ of rotations and translations fall within one of the two major categories.

COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos

no code implementations ICCV 2023 Boxiao Pan, Bokui Shen, Davis Rempe, Despoina Paschalidou, Kaichun Mo, Yanchao Yang, Leonidas J. Guibas

In this work, we introduce the challenging problem of predicting collisions in diverse environments from multi-view egocentric videos captured from body-mounted cameras.

Synthetic Data Generation

6D Camera Relocalization in Visually Ambiguous Extreme Environments

no code implementations13 Jul 2022 Yang Zheng, Tolga Birdal, Fei Xia, Yanchao Yang, Yueqi Duan, Leonidas J. Guibas

To this end, we propose: (i) a hierarchical localization system, where we leverage temporal information and (ii) a novel environment-aware image enhancement method to boost the robustness and accuracy.

Camera Relocalization Image Enhancement

Object Scene Representation Transformer

no code implementations14 Jun 2022 Mehdi S. M. Sajjadi, Daniel Duckworth, Aravindh Mahendran, Sjoerd van Steenkiste, Filip Pavetić, Mario Lučić, Leonidas J. Guibas, Klaus Greff, Thomas Kipf

A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition.

Novel View Synthesis Representation Learning

Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction

no code implementations CVPR 2022 Yining Hong, Kaichun Mo, Li Yi, Leonidas J. Guibas, Antonio Torralba, Joshua B. Tenenbaum, Chuang Gan

Specifically, FixNet consists of a perception module to extract the structured representation from the 3D point cloud, a physical dynamics prediction module to simulate the results of interactions on 3D objects, and a functionality prediction module to evaluate the functionality and choose the correct fix.

GIMO: Gaze-Informed Human Motion Prediction in Context

1 code implementation20 Apr 2022 Yang Zheng, Yanchao Yang, Kaichun Mo, Jiaman Li, Tao Yu, Yebin Liu, C. Karen Liu, Leonidas J. Guibas

We perform an extensive study of the benefits of leveraging the eye gaze for ego-centric human motion prediction with various state-of-the-art architectures.

Human motion prediction motion prediction

ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation

no code implementations14 Mar 2022 Bokui Shen, Zhenyu Jiang, Christopher Choy, Leonidas J. Guibas, Silvio Savarese, Anima Anandkumar, Yuke Zhu

Manipulating volumetric deformable objects in the real world, like plush toys and pizza dough, bring substantial challenges due to infinite shape variations, non-rigid motions, and partial observability.

Contrastive Learning Deformable Object Manipulation

ADeLA: Automatic Dense Labeling With Attention for Viewpoint Shift in Semantic Segmentation

no code implementations CVPR 2022 Hanxiang Ren, Yanchao Yang, He Wang, Bokui Shen, Qingnan Fan, Youyi Zheng, C. Karen Liu, Leonidas J. Guibas

We describe a method to deal with performance drop in semantic segmentation caused by viewpoint changes within multi-camera systems, where temporally paired images are readily available, but the annotations may only be abundant for a few typical views.

Semantic Segmentation Unsupervised Domain Adaptation

Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior

no code implementations CVPR 2022 Davis Rempe, Jonah Philion, Leonidas J. Guibas, Sanja Fidler, Or Litany

Scenario generation is formulated as an optimization in the latent space of this traffic model, perturbing an initial real-world scene to produce trajectories that collide with a given planner.

Autonomous Vehicles

Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization

1 code implementation25 Nov 2021 Jiahui Huang, Tolga Birdal, Zan Gojcic, Leonidas J. Guibas, Shi-Min Hu

We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds.

Point Cloud Registration

Unsupervised Discovery of Object Radiance Fields

1 code implementation ICLR 2022 Hong-Xing Yu, Leonidas J. Guibas, Jiajun Wu

We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision.

Novel View Synthesis Scene Segmentation

A Functional Approach to Rotation Equivariant Non-Linearities for Tensor Field Networks.

no code implementations CVPR 2021 Adrien Poulenard, Leonidas J. Guibas

A fundamental problem in equivariant deep learning is to design activation functions which are both informative and preserve equivariance.

CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds

1 code implementation ICCV 2021 Yijia Weng, He Wang, Qiang Zhou, Yuzhe Qin, Yueqi Duan, Qingnan Fan, Baoquan Chen, Hao Su, Leonidas J. Guibas

For the first time, we propose a unified framework that can handle 9DoF pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories.

Pose Tracking

Weakly Supervised Learning of Rigid 3D Scene Flow

1 code implementation CVPR 2021 Zan Gojcic, Or Litany, Andreas Wieser, Leonidas J. Guibas, Tolga Birdal

We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies.

Autonomous Driving Scene Flow Estimation +2

3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection

2 code implementations CVPR 2021 He Wang, Yezhen Cong, Or Litany, Yue Gao, Leonidas J. Guibas

On KITTI, we are the first to demonstrate semi-supervised 3D object detection and our method surpasses a fully supervised baseline from 1. 8% to 7. 6% under different label ratios and categories.

3D Object Detection Autonomous Driving +1

ShapeFlow: Learnable Deformation Flows Among 3D Shapes

no code implementations NeurIPS 2020 Chiyu Jiang, Jingwei Huang, Andrea Tagliasacchi, Leonidas J. Guibas

Such a space naturally allows the disentanglement of geometric style (coming from the source) and structural pose (conforming to the target).

Disentanglement Style Transfer

A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries

no code implementations15 Oct 2020 Ali Kashefi, Davis Rempe, Leonidas J. Guibas

Grid vertices in a computational fluid dynamics (CFD) domain are viewed as point clouds and used as inputs to a neural network based on the PointNet architecture, which learns an end-to-end mapping between spatial positions and CFD quantities.

IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration

2 code implementations11 Oct 2020 Ziyi Wu, Yueqi Duan, He Wang, Qingnan Fan, Leonidas J. Guibas

The former aims to recover the surface of point cloud through implicit function, while the latter encourages evenly-distributed points.

Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images

1 code implementation ECCV 2020 Jiahui Lei, Srinath Sridhar, Paul Guerrero, Minhyuk Sung, Niloy Mitra, Leonidas J. Guibas

We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views.

DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation

1 code implementation12 Aug 2020 Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao

While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structure, in a controllable manner.

3D Shape Generation

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

1 code implementation NeurIPS 2020 Davis Rempe, Tolga Birdal, Yongheng Zhao, Zan Gojcic, Srinath Sridhar, Leonidas J. Guibas

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects.

Pose Estimation

Contact and Human Dynamics from Monocular Video

1 code implementation ECCV 2020 Davis Rempe, Leonidas J. Guibas, Aaron Hertzmann, Bryan Russell, Ruben Villegas, Jimei Yang

Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetrating the ground and bodies leaning at extreme angles.

Human Dynamics Pose Estimation

PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding

2 code implementations ECCV 2020 Saining Xie, Jiatao Gu, Demi Guo, Charles R. Qi, Leonidas J. Guibas, Or Litany

To this end, we select a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes.

Point Cloud Pre-training Representation Learning +3

Object-Centric Multi-View Aggregation

no code implementations20 Jul 2020 Shubham Tulsiani, Or Litany, Charles R. Qi, He Wang, Leonidas J. Guibas

We present an approach for aggregating a sparse set of views of an object in order to compute a semi-implicit 3D representation in the form of a volumetric feature grid.

Novel View Synthesis Pose Estimation

Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks

no code implementations12 Jun 2020 He Wang, Zetian Jiang, Li Yi, Kaichun Mo, Hao Su, Leonidas J. Guibas

We further study how different evaluation metrics weigh the sampling pattern against the geometry and propose several perceptual metrics forming a sampling spectrum of metrics.


PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions

1 code implementation ECCV 2020 Kaichun Mo, He Wang, Xinchen Yan, Leonidas J. Guibas

3D generative shape modeling is a fundamental research area in computer vision and interactive computer graphics, with many real-world applications.

3D Shape Generation

Curriculum DeepSDF

1 code implementation ECCV 2020 Yueqi Duan, Haidong Zhu, He Wang, Li Yi, Ram Nevatia, Leonidas J. Guibas

When learning to sketch, beginners start with simple and flexible shapes, and then gradually strive for more complex and accurate ones in the subsequent training sessions.

3D Shape Representation Representation Learning

SAPIEN: A SimulAted Part-based Interactive ENvironment

1 code implementation CVPR 2020 Fanbo Xiang, Yuzhe Qin, Kaichun Mo, Yikuan Xia, Hao Zhu, Fangchen Liu, Minghua Liu, Hanxiao Jiang, Yifu Yuan, He Wang, Li Yi, Angel X. Chang, Leonidas J. Guibas, Hao Su

To achieve this task, a simulated environment with physically realistic simulation, sufficient articulated objects, and transferability to the real robot is indispensable.

ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes

1 code implementation CVPR 2020 Charles R. Qi, Xinlei Chen, Or Litany, Leonidas J. Guibas

Compared to prior work on multi-modal detection, we explicitly extract both geometric and semantic features from the 2D images.

Ranked #2 on 3D Object Detection on SUN-RGBD (using extra training data)

3D Object Detection object-detection +1

Predicting the Physical Dynamics of Unseen 3D Objects

1 code implementation16 Jan 2020 Davis Rempe, Srinath Sridhar, He Wang, Leonidas J. Guibas

Experiments show that we can accurately predict the changes in state for unseen object geometries and initial conditions.

A Condition Number for Joint Optimization of Cycle-Consistent Networks

1 code implementation NeurIPS 2019 Leonidas J. Guibas, Qi-Xing Huang, Zhenxiao Liang

A recent trend in optimizing maps such as dense correspondences between objects or neural networks between pairs of domains is to optimize them jointly.

StructEdit: Learning Structural Shape Variations

1 code implementation CVPR 2020 Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas

Learning to encode differences in the geometry and (topological) structure of the shapes of ordinary objects is key to generating semantically plausible variations of a given shape, transferring edits from one shape to another, and many other applications in 3D content creation.

Situational Fusion of Visual Representation for Visual Navigation

no code implementations ICCV 2019 Bokui Shen, Danfei Xu, Yuke Zhu, Leonidas J. Guibas, Li Fei-Fei, Silvio Savarese

A complex visual navigation task puts an agent in different situations which call for a diverse range of visual perception abilities.

Visual Navigation

StructureNet: Hierarchical Graph Networks for 3D Shape Generation

2 code implementations1 Aug 2019 Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas

We introduce StructureNet, a hierarchical graph network which (i) can directly encode shapes represented as such n-ary graphs; (ii) can be robustly trained on large and complex shape families; and (iii) can be used to generate a great diversity of realistic structured shape geometries.

3D Shape Generation

Multiview Aggregation for Learning Category-Specific Shape Reconstruction

1 code implementation NeurIPS 2019 Srinath Sridhar, Davis Rempe, Julien Valentin, Sofien Bouaziz, Leonidas J. Guibas

We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances.

3D Shape Reconstruction

A Topology Layer for Machine Learning

3 code implementations29 May 2019 Rickard Brüel-Gabrielsson, Bradley J. Nelson, Anjan Dwaraknath, Primoz Skraba, Leonidas J. Guibas, Gunnar Carlsson

Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning.

BIG-bench Machine Learning

ShapeGlot: Learning Language for Shape Differentiation

1 code implementation ICCV 2019 Panos Achlioptas, Judy Fan, Robert X. D. Hawkins, Noah D. Goodman, Leonidas J. Guibas

We also find that these models are amenable to zero-shot transfer learning to novel object classes (e. g. transfer from training on chairs to testing on lamps), as well as to real-world images drawn from furniture catalogs.

Transfer Learning

An Information-Theoretic Metric of Transferability for Task Transfer Learning

1 code implementation ICLR 2019 Yajie Bao, Yang Li, Shao-Lun Huang, Lin Zhang, Amir R. Zamir, Leonidas J. Guibas

An important question in task transfer learning is to determine task transferability, i. e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task.

General Classification Scene Understanding +1

DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces

2 code implementations12 Jan 2019 Jun Gao, Chengcheng Tang, Vignesh Ganapathi-Subramanian, Jiahui Huang, Hao Su, Leonidas J. Guibas

Reconstruction of geometry based on different input modes, such as images or point clouds, has been instrumental in the development of computer aided design and computer graphics.

Learning Generalizable Physical Dynamics of 3D Rigid Objects

no code implementations2 Jan 2019 Davis Rempe, Srinath Sridhar, He Wang, Leonidas J. Guibas

In this work, we focus on predicting the dynamics of 3D rigid objects, in particular an object's final resting position and total rotation when subjected to an impulsive force.

Autonomous Vehicles

Topology-Aware Surface Reconstruction for Point Clouds

no code implementations29 Nov 2018 Rickard Brüel Gabrielsson, Vignesh Ganapathi-Subramanian, Primoz Skraba, Leonidas J. Guibas

We present an approach to inform the reconstruction of a surface from a point scan through topological priors.

Computational Geometry Graphics

Modular Latent Spaces for Shape Correspondences

1 code implementation Symposium in Geometry Processing 2018 2018 Vignesh Ganapathi-Subramanian, Olga Diamanti, Leonidas J. Guibas

To achieve this, we use intermediate nonlinear embedding spaces, computed individually on every shape; the embedding functions use ideas from diffusion geometry and capture how different descriptors on the same shape inter‐relate.

FlowNet3D: Learning Scene Flow in 3D Point Clouds

10 code implementations CVPR 2019 Xingyu Liu, Charles R. Qi, Leonidas J. Guibas

In this work, we propose a novel deep neural network named $FlowNet3D$ that learns scene flow from point clouds in an end-to-end fashion.

Motion Segmentation

Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning

no code implementations CVPR 2018 Chuang Gan, Boqing Gong, Kun Liu, Hao Su, Leonidas J. Guibas

In addition, we also find that a progressive training strategy can foster a better neural network for the video recognition task than blindly pooling the distinct sources of geometry cues together.

Action Recognition Representation Learning +5

Learning Shape Abstractions by Assembling Volumetric Primitives

4 code implementations CVPR 2017 Shubham Tulsiani, Hao Su, Leonidas J. Guibas, Alexei A. Efros, Jitendra Malik

We present a learning framework for abstracting complex shapes by learning to assemble objects using 3D volumetric primitives.

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.

Volumetric and Multi-View CNNs for Object Classification on 3D Data

2 code implementations CVPR 2016 Charles R. Qi, Hao Su, Matthias Niessner, Angela Dai, Mengyuan Yan, Leonidas J. Guibas

Empirical results from these two types of CNNs exhibit a large gap, indicating that existing volumetric CNN architectures and approaches are unable to fully exploit the power of 3D representations.

3D Object Recognition 3D Point Cloud Classification +1

3D-Assisted Feature Synthesis for Novel Views of an Object

no code implementations ICCV 2015 Hao Su, Fan Wang, Eric Yi, Leonidas J. Guibas

Comparing two images from different views has been a long-standing challenging problem in computer vision, as visual features are not stable under large view point changes.

Image Retrieval Retrieval

Unsupervised Multi-Class Joint Image Segmentation

no code implementations CVPR 2014 Fan Wang, Qi-Xing Huang, Maks Ovsjanikov, Leonidas J. Guibas

Joint segmentation of image sets is a challenging problem, especially when there are multiple objects with variable appearance shared among the images in the collection and the set of objects present in each particular image is itself varying and unknown.

Image Segmentation Semantic Segmentation

Near-Optimal Joint Object Matching via Convex Relaxation

no code implementations6 Feb 2014 Yuxin Chen, Leonidas J. Guibas, Qi-Xing Huang

Joint matching over a collection of objects aims at aggregating information from a large collection of similar instances (e. g. images, graphs, shapes) to improve maps between pairs of them.

Wavelets on Graphs via Deep Learning

no code implementations NeurIPS 2013 Raif Rustamov, Leonidas J. Guibas

An increasing number of applications require processing of signals defined on weighted graphs.

WaldHash: sequential similarity-preserving hashing

no code implementations CIS 2010 Alexander M. Bronstein, Michael M. Bronstein, Leonidas J. Guibas, and Maks Ovsjanikov

Similarity-sensitive hashing seeks compact representation of vector data as binary codes, so that the Hamming distance between code words approximates the original similarity.

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