AIConfPaper
← Search

Keisuke Tateno

18 accepted papers

2026

DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management

Casimir Feldmann, Maximum Wilder-Smith, Vaishakh Patil, Michael Oechsle, Michael Niemeyer, Keisuke Tateno +1
RA-L 2026

Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated impressive results for novel view synthesis with real-time rendering capabilities. However, integrating 3DGS with SLAM systems faces a fundamental scalability limitation: methods are constrained by GPU memory capacity, restricting rec

Cited by 1Source ↗code ↗Scholar ↗
2026

DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds

Weirong Chen, Keisuke Tateno, Hidenobu Matsuki, Michael Niemeyer, Daniel Cremers, Federico Tombari
ICML 2026poster

We address the problem of 4D reconstruction from partial point cloud sequences, where observations from depth sensors are incomplete, unordered, and lack explicit point correspondence over time. Recovering coherent 4D geometry in this geometry-only setting is challenging due to missing observations …

Cited by 0Source ↗Scholar ↗
2026

RiemanLine: Riemannian Manifold Representation of 3D Lines for Factor Graph Optimization

Yan Li, Ze Yang, Keisuke Tateno, Federico Tombari, Liang Zhao, Gim Hee Lee
AAAI 2026technical

Minimal parametrization of 3D lines plays a critical role in camera localization and structural mapping. Existing representations in robotics and computer vision predominantly handle independent lines, overlooking structural regularities such as sets of parallel lines that are pervasive in man-made

Cited by 0Source ↗PDF ↗Scholar ↗
2025

HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild

Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno, Francis Engelmann, Leonidas Guibas
NeurIPS 2025poster

Current 3D layout estimation models are predominantly trained on synthetic datasets biased toward simplistic, single-floor scenes. This prevents them from generalizing to complex, multi-floor buildings, often forcing a per-floor processing approach that sacrifices global context. Few works have atte…

Cited by 0Source ↗Scholar ↗
2025

Learning Neural Exposure Fields for View Synthesis

Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona, Michael Oechsle, Christina Tsalicoglou, Keisuke Tateno +2
NeurIPS 2025poster

Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and view synthesis. Despite achieving high-quality results for common benchmarks with curated data, outputs often degrade for data that contain per image variations such as strong exposure changes,…

Cited by 0Source ↗Scholar ↗
2024

Diffusion Bridges for 3D Point Cloud Denoising

Mathias Vogel Hüni, Keisuke Tateno, Marc Pollefeys, Federico Tombari, Marie-Julie Rakotosaona, Francis Engelmann*
ECCV 2024poster

"In this work, we address the task of point cloud denoising using a novel framework adapting Diffusion Schrödinger bridges to unstructured data like point sets. Unlike previous works that predict point-wise displacements from point features or learned noise distributions, our method learns an optim…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAM

Hidenobu Matsuki, Keisuke Tateno, Michael Niemeyer, Federico Tombari
RA-L 2024

Neural field-based 3D representations have recently been adopted in many areas including SLAM systems. Current neural SLAM or online mapping systems lead to impressive results in the presence of simple captures, but they rely on a world-centric map representation as only a single neural field model

Cited by 25Source ↗Scholar ↗
2024

OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views

Francis Engelmann, Fabian Manhardt, Michael Niemeyer, Keisuke Tateno, Federico Tombari
ICLR 2024poster

Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only segment classes from a pre-defined training set. More recently, fi…

Cited by 33Source ↗PDF ↗Scholar ↗
2023

Incremental 3D Semantic Scene Graph Prediction From RGB Sequences

Shun-Cheng Wu, Keisuke Tateno, Nassir Navab, Federico Tombari
CVPR 2023poster

3D semantic scene graphs are a powerful holistic representation as they describe the individual objects and depict the relation between them. They are compact high-level graphs that enable many tasks requiring scene reasoning. In real-world settings, existing 3D estimation methods produce robust pre…

Cited by 25Source ↗PDF ↗code ↗Scholar ↗
2023

Towards Long-Term Retrieval-Based Visual Localization in Indoor Environments With Changes

Julia Kabalar, Shun-Cheng Wu, Johanna Wald, Keisuke Tateno, Nassir Navab, Federico Tombari
RA-L 2023

Visual localization is a challenging task due to the presence of illumination changes, occlusion, and perception from novel viewpoints. Re-localizing the camera pose in long-term setups raises difficulties caused by changes in scene appearance and geometry introduced by human or natural deterioratio

Cited by 12Source ↗Scholar ↗
2021

SceneGraphFusion: Incremental 3D Scene Graph Prediction From RGB-D Sequences

Shun-Cheng Wu, Johanna Wald, Keisuke Tateno, Nassir Navab, Federico Tombari
CVPR 2021poster

Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks. This work proposes a method to build up semantic scene graphs from a 3D environment incrementally given a sequence of RGB-D frames. To this end, we aggregate PointNet features from…

Cited by 186PDF ↗Scholar ↗
2018

Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images

Keisuke Tateno, Nassir Navab, Federico Tombari
ECCV 2018poster

There is a high demand of 3D data for 360° panoramic images and videos, pushed by the growing availability on the market of specialized hardware for both capturing (e.g., omnidirectional cameras) as well as visualizing in 3D (e.g., head mounted displays) panoramic images and videos. At the same time…

Cited by 221Source ↗PDF ↗Scholar ↗
2018

Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation

Yoshikatsu Nakajima, Keisuke Tateno, Federico Tombari, Hideo Saito
IROS 2018poster

We propose an efficient and scalable method for incrementally building a dense, semantically annotated 3D map in real-time. The proposed method assigns class probabilities to each region, not each element (e.g., surfel and voxel), of the 3D map which is built up through a robust SLAM framework and i…

Cited by 51Source ↗Scholar ↗
2018

Real-Time Fully Incremental Scene Understanding on Mobile Platforms

Johanna Wald, Keisuke Tateno, Jürgen Sturm, Nassir Navab, Federico Tombari
RA-L 2018

We propose an online RGB-D based scene understanding method for indoor scenes running in real time on mobile devices. First, we incrementally reconstruct the scene via simultaneous localization and mapping and compute a three-dimensional (3-D) geometric segmentation by fusing segments obtained from

Cited by 30Source ↗Scholar ↗
2017

CNN-SLAM: Real-Time Dense Monocular SLAM With Learned Depth Prediction

Keisuke Tateno, Federico Tombari, Iro Laina, Nassir Navab
CVPR 2017spotlight

Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for the goal of accurate and dense monocular reconstruction. We propose a method where CNN-predicted dense depth maps a…

Cited by 1024PDF ↗code ↗Scholar ↗
2016

Incremental scene understanding on dense SLAM

Chi Li, Han Xiao, Keisuke Tateno, Federico Tombari, Nassir Navab, Gregory D. Hager
IROS 2016poster

We present an architecture for online, incremental scene modeling which combines a SLAM-based scene understanding framework with semantic segmentation and object pose estimation. The core of this approach comprises a probabilistic inference scheme that predicts semantic labels for object hypotheses…

Cited by 36Source ↗Scholar ↗
2016

When 2.5D is not enough: Simultaneous reconstruction, segmentation and recognition on dense SLAM

Keisuke Tateno, Federico Tombari, Nassir Navab
ICRA 2016

While the main trend of 3D object recognition has been to infer object detection from single views of the scene - i.e., 2.5D data - this work explores the direction on performing object recognition on 3D data that is reconstructed from multiple viewpoints, under the conjecture that such data can imp

Cited by 95Source ↗Scholar ↗