Search Results for author: Yasutaka Furukawa

Found 46 papers, 29 papers with code

Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction

1 code implementation ECCV 2020 Yiming Qian, Yasutaka Furukawa

This paper proposes a novel single-image piecewise planar reconstruction technique that infers and enforces inter-plane relationships.


RetailOpt: An Opt-In, Easy-to-Deploy Trajectory Estimation System Leveraging Smartphone Motion Data and Retail Facility Information

no code implementations19 Apr 2024 Ryo Yonetani, Jun Baba, Yasutaka Furukawa

We present RetailOpt, a novel opt-in, easy-to-deploy system for tracking customer movements in indoor retail environments.

MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping

no code implementations23 Mar 2024 Jiacheng Chen, Yuefan Wu, Jiaqi Tan, Hang Ma, Yasutaka Furukawa

The paper further makes benchmark contributions by 1) Improving processing code for existing datasets to produce consistent ground truth with temporal alignments and 2) Augmenting existing mAP metrics with consistency checks.

MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

no code implementations20 Feb 2024 Shitao Tang, Jiacheng Chen, Dilin Wang, Chengzhou Tang, Fuyang Zhang, Yuchen Fan, Vikas Chandra, Yasutaka Furukawa, Rakesh Ranjan

MVDiffusion++ achieves superior flexibility and scalability with two surprisingly simple ideas: 1) A ``pose-free architecture'' where standard self-attention among 2D latent features learns 3D consistency across an arbitrary number of conditional and generation views without explicitly using camera pose information; and 2) A ``view dropout strategy'' that discards a substantial number of output views during training, which reduces the training-time memory footprint and enables dense and high-resolution view synthesis at test time.

3D Object Reconstruction 3D Reconstruction +2

BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry

1 code implementation28 Jan 2024 Xiang Xu, Joseph G. Lambourne, Pradeep Kumar Jayaraman, Zhengqing Wang, Karl D. D. Willis, Yasutaka Furukawa

Starting from the root and progressing to the leaf, BrepGen employs Transformer-based diffusion models to sequentially denoise node features while duplicated nodes are detected and merged, recovering the B-Rep topology information.

A-Scan2BIM: Assistive Scan to Building Information Modeling

no code implementations30 Nov 2023 Weilian Song, Jieliang Luo, Dale Zhao, Yan Fu, Chin-Yi Cheng, Yasutaka Furukawa

This paper proposes an assistive system for architects that converts a large-scale point cloud into a standardized digital representation of a building for Building Information Modeling (BIM) applications.

Model Editing

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

1 code implementation NeurIPS 2023 Shitao Tang, Fuyang Zhang, Jiacheng Chen, Peng Wang, Yasutaka Furukawa

This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e. g., perspective crops from a panorama or multi-view images given depth maps and poses).

Image Generation

Hierarchical Neural Coding for Controllable CAD Model Generation

1 code implementation30 Jun 2023 Xiang Xu, Pradeep Kumar Jayaraman, Joseph G. Lambourne, Karl D. D. Willis, Yasutaka Furukawa

This paper presents a novel generative model for Computer Aided Design (CAD) that 1) represents high-level design concepts of a CAD model as a three-level hierarchical tree of neural codes, from global part arrangement down to local curve geometry; and 2) controls the generation or completion of CAD models by specifying the target design using a code tree.

PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models

1 code implementation NeurIPS 2023 Jiacheng Chen, Ruizhi Deng, Yasutaka Furukawa

This paper presents PolyDiffuse, a novel structured reconstruction algorithm that transforms visual sensor data into polygonal shapes with Diffusion Models (DM), an emerging machinery amid exploding generative AI, while formulating reconstruction as a generation process conditioned on sensor data.

HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising

1 code implementation CVPR 2023 Mohammad Amin Shabani, Sepidehsadat Hosseini, Yasutaka Furukawa

The paper presents a novel approach for vector-floorplan generation via a diffusion model, which denoises 2D coordinates of room/door corners with two inference objectives: 1) a single-step noise as the continuous quantity to precisely invert the continuous forward process; and 2) the final 2D coordinate as the discrete quantity to establish geometric incident relationships such as parallelism, orthogonality, and corner-sharing.

Denoising Vector Graphics

NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization

1 code implementation CVPR 2023 Shitao Tang, Sicong Tang, Andrea Tagliasacchi, Ping Tan, Yasutaka Furukawa

State-of-the-art feature matching methods require each scene to be stored as a 3D point cloud with per-point features, consuming several gigabytes of storage per scene.

Camera Localization Decoder +1

SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks

no code implementations11 Jul 2022 Xiang Xu, Karl D. D. Willis, Joseph G. Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, Yasutaka Furukawa

We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences containing sketch-and-extrude modeling operations.

Efficient Exploration

Floorplan Restoration by Structure Hallucinating Transformer Cascades

no code implementations1 Jun 2022 Sepidehsadat Hosseini, Yasutaka Furukawa

This paper presents an extreme floorplan reconstruction task, a new benchmark for the task, and a neural architecture as a solution.

Neural Inertial Localization

1 code implementation CVPR 2022 Sachini Herath, David Caruso, Chen Liu, Yufan Chen, Yasutaka Furukawa

This paper proposes the inertial localization problem, the task of estimating the absolute location from a sequence of inertial sensor measurements.

Indoor Localization Privacy Preserving

HEAT: Holistic Edge Attention Transformer for Structured Reconstruction

1 code implementation CVPR 2022 Jiacheng Chen, Yiming Qian, Yasutaka Furukawa

This paper presents a novel attention-based neural network for structured reconstruction, which takes a 2D raster image as an input and reconstructs a planar graph depicting an underlying geometric structure.

Edge Classification Extracting Buildings In Remote Sensing Images +1

Structured Outdoor Architecture Reconstruction by Exploration and Classification

1 code implementation ICCV 2021 Fuyang Zhang, Xiang Xu, Nelson Nauata, Yasutaka Furukawa

This paper presents an explore-and-classify framework for structured architectural reconstruction from an aerial image.


Plan2Scene: Converting Floorplans to 3D Scenes

1 code implementation CVPR 2021 Madhawa Vidanapathirana, Qirui Wu, Yasutaka Furukawa, Angel X. Chang, Manolis Savva

We address the task of converting a floorplan and a set of associated photos of a residence into a textured 3D mesh model, a task which we call Plan2Scene.


Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments

1 code implementation18 May 2021 Sachini Herath, Saghar Irandoust, Bowen Chen, Yiming Qian, Pyojin Kim, Yasutaka Furukawa

The paper proposes a multi-modal sensor fusion algorithm that fuses WiFi, IMU, and floorplan information to infer an accurate and dense location history in indoor environments.

Sensor Fusion

Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation

1 code implementation CVPR 2021 Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, Ken Sakurada

This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable computations in a convolutional architecture.

Clustering object-detection +5

House-GAN++: Generative Adversarial Layout Refinement Networks

1 code implementation3 Mar 2021 Nelson Nauata, Sepidehsadat Hosseini, Kai-Hung Chang, Hang Chu, Chin-Yi Cheng, Yasutaka Furukawa

This paper proposes a novel generative adversarial layout refinement network for automated floorplan generation.

Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses

1 code implementation CVPR 2021 Yiming Qian, Hao Zhang, Yasutaka Furukawa

This paper presents Roof-GAN, a novel generative adversarial network that generates structured geometry of residential roof structures as a set of roof primitives and their relationships.

Generative Adversarial Network

House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation

1 code implementation ECCV 2020 Nelson Nauata, Kai-Hung Chang, Chin-Yi Cheng, Greg Mori, Yasutaka Furukawa

This paper proposes a novel graph-constrained generative adversarial network, whose generator and discriminator are built upon relational architecture.

Generative Adversarial Network

Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference

2 code implementations ECCV 2020 Nelson Nauata, Yasutaka Furukawa

This paper tackles a 2D architecture vectorization problem, whose task is to infer an outdoor building architecture as a 2D planar graph from a single RGB image.

Graph Reconstruction

Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path

1 code implementation ICCV 2019 Jiacheng Chen, Chen Liu, Jiaye Wu, Yasutaka Furukawa

This paper proposes a new approach for automated floorplan reconstruction from RGBD scans, a major milestone in indoor mapping research.

Edge Detection

RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, and New Methods

3 code implementations30 May 2019 Hang Yan, Sachini Herath, Yasutaka Furukawa

This paper sets a new foundation for data-driven inertial navigation research, where the task is the estimation of positions and orientations of a moving subject from a sequence of IMU sensor measurements.

MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation

1 code implementation12 Feb 2019 Chen Liu, Yasutaka Furukawa

We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance.

3D Instance Segmentation Clustering +2

PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image

2 code implementations CVPR 2019 Chen Liu, Kihwan Kim, Jinwei Gu, Yasutaka Furukawa, Jan Kautz

This paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs piecewise planar surfaces from a single RGB image.

3D Plane Detection 3D Reconstruction +1

Neural Procedural Reconstruction for Residential Buildings

no code implementations ECCV 2018 Huayi Zeng, Jiaye Wu, Yasutaka Furukawa

This paper proposes a novel 3D reconstruction approach, dubbed Neural Procedural Reconstruction (NPR), which trains deep neural networks to procedurally apply shape grammar rules and reconstruct CAD-quality models from 3D points.

3D Reconstruction

Polarimetric Dense Monocular SLAM

no code implementations CVPR 2018 Luwei Yang, Feitong Tan, Ao Li, Zhaopeng Cui, Yasutaka Furukawa, Ping Tan

This paper presents a novel polarimetric dense monocular SLAM (PDMS) algorithm based on a polarization camera.

PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image

1 code implementation CVPR 2018 Chen Liu, Jimei Yang, Duygu Ceylan, Ersin Yumer, Yasutaka Furukawa

The proposed end-to-end DNN learns to directly infer a set of plane parameters and corresponding plane segmentation masks from a single RGB image.

Depth Estimation Depth Prediction +1

FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans

2 code implementations ECCV 2018 Chen Liu, Jiaye Wu, Yasutaka Furukawa

The ultimate goal of this indoor mapping research is to automatically reconstruct a floorplan simply by walking through a house with a smartphone in a pocket.

Vector Graphics

RIDI: Robust IMU Double Integration

1 code implementation ECCV 2018 Hang Yan, Qi Shan, Yasutaka Furukawa

This paper proposes a novel data-driven approach for inertial navigation, which learns to estimate trajectories of natural human motions just from an inertial measurement unit (IMU) in every smartphone.

Raster-To-Vector: Revisiting Floorplan Transformation

1 code implementation ICCV 2017 Chen Liu, Jiajun Wu, Pushmeet Kohli, Yasutaka Furukawa

A neural architecture first transforms a rasterized image to a set of junctions that represent low-level geometric and semantic information (e. g., wall corners or door end-points).

Vector Graphics

Exploiting 2D Floorplan for Building-scale Panorama RGBD Alignment

1 code implementation CVPR 2017 Erik Wijmans, Yasutaka Furukawa

To the best of our knowledge, we present the first effective system that utilizes a 2D floorplan image for building-scale 3D pointcloud alignment.

Deep Multi-Modal Image Correspondence Learning

no code implementations5 Dec 2016 Chen Liu, Jiajun Wu, Pushmeet Kohli, Yasutaka Furukawa

Our result implies that neural networks are effective at perceptual tasks that require long periods of reasoning even for humans to solve.

Turning an Urban Scene Video into a Cinemagraph

no code implementations CVPR 2017 Hang Yan, Yebin Liu, Yasutaka Furukawa

Our approach first warps an input video into the viewpoint of a reference camera.

Panoramic Structure from Motion via Geometric Relationship Detection

no code implementations5 Dec 2016 Satoshi Ikehata, Ivaylo Boyadzhiev, Qi Shan, Yasutaka Furukawa

This paper addresses the problem of Structure from Motion (SfM) for indoor panoramic image streams, extremely challenging even for the state-of-the-art due to the lack of textures and minimal parallax.

Relationship Detection

Multi-way Particle Swarm Fusion

no code implementations5 Dec 2016 Chen Liu, Hang Yan, Pushmeet Kohli, Yasutaka Furukawa

This paper proposes a novel MAP inference framework for Markov Random Field (MRF) in parallel computing environments.

Optical Flow Estimation

Layered Scene Decomposition via the Occlusion-CRF

no code implementations CVPR 2016 Chen Liu, Pushmeet Kohli, Yasutaka Furukawa

This paper addresses the challenging problem of perceiving the hidden or occluded geometry of the scene depicted in any given RGBD image.

Image Segmentation Semantic Segmentation

Structured Indoor Modeling

no code implementations ICCV 2015 Satoshi Ikehata, Hang Yang, Yasutaka Furukawa

The grammar then drives a principled new reconstruction algorithm, where the grammar rules are sequentially applied to recover a structured model.

Piecewise Planar and Compact Floorplan Reconstruction from Images

no code implementations CVPR 2014 Ricardo Cabral, Yasutaka Furukawa

The second challenge is the need of a sophisti- cated regularization technique that enforces piecewise pla- narity, to suppress clutter and yield high quality texture mapped models.

Occluding Contours for Multi-View Stereo

no code implementations CVPR 2014 Qi Shan, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, Steven M. Seitz

The proposed approach outperforms state of the art MVS techniques for challenging Internet datasets, yielding dramatic quality improvements both around object contours and in surface detail.

Surface Reconstruction

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