Ryohei Sasaki@engineer's banner

Ryohei Sasaki@engineer

@rsasaki0109 • 10,869 subscribers

Software Engineer at MAP IV(TIER IV group). Previously, Waseda University. AI/Robotics/Autonomous Driving/GNSS/LiDAR/Camera/IMU/SLAM/Localization/Mapping

Shorts

RaCo: Ranking and Covariance for Practical Learned Keypoints(3DV 2026) RaCo is a rotationally equivariant keypoint detector that identifies stable and repeatable keypoints in images. Refer the paper for a quantitative evaluation of its rotational equivariance.

RaCo: Ranking and Covariance for Practical Learned Keypoints(3DV 2026) RaCo is a rotationally equivariant keypoint detector that identifies stable and repeatable keypoints in images. Refer the paper for a quantitative evaluation of its rotational equivariance.

112,136 次观看

RoadScan-AI-Automated-Pothole-Detection-Tracking RoadScan AI is a computer vision system built to automatically detect and track potholes in road footage — including dashcam, drone, and fixed-camera video. At its core, the system uses a YOLO11n model fine-tuned on a custom pothole dataset, paired with ByteTrack for multi-object tracking. This enables the system to maintain a consistent identity for each pothole across frames rather than treating every detection as a new, isolated event.

RoadScan-AI-Automated-Pothole-Detection-Tracking RoadScan AI is a computer vision system built to automatically detect and track potholes in road footage — including dashcam, drone, and fixed-camera video. At its core, the system uses a YOLO11n model fine-tuned on a custom pothole dataset, paired with ByteTrack for multi-object tracking. This enables the system to maintain a consistent identity for each pothole across frames rather than treating every detection as a new, isolated event.

103,374 次观看

SuperMap: A Living Spatial Memory for Embodied AI RSS 2026 Carnegie Mellon University SuperMap is a living spatial memory for embodied AI. It perceives the world, remembers its evolution, and supports reasoning and action. It is a training-free spatio-temporal SLAM system that builds a persistent semantic world model. It fuses high-frequency geometric SLAM with asynchronous open-vocabulary perception, producing a 4D scene graph: a queryable map carrying spatial and temporal information for every object, enabling visual-language navigation and long-horizon reasoning on real robots.

SuperMap: A Living Spatial Memory for Embodied AI RSS 2026 Carnegie Mellon University SuperMap is a living spatial memory for embodied AI. It perceives the world, remembers its evolution, and supports reasoning and action. It is a training-free spatio-temporal SLAM system that builds a persistent semantic world model. It fuses high-frequency geometric SLAM with asynchronous open-vocabulary perception, producing a 4D scene graph: a queryable map carrying spatial and temporal information for every object, enabling visual-language navigation and long-horizon reasoning on real robots.

25,581 次观看

UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization(ECCV 2026) UniSim-SLAM applied to an image sequence captured with a mobile phone.

UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization(ECCV 2026) UniSim-SLAM applied to an image sequence captured with a mobile phone.

12,722 次观看

ge-gnss-visibility GNSS satellite visibility simulation from Google Earth

ge-gnss-visibility GNSS satellite visibility simulation from Google Earth

69,775 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Inflatable Whole-Body Robotic Skin with Internal Time-of-Flight (ToF) Depth Sensing and Kinematics-Based Point-Cloud Prediction(IROS2026) An inflatable Baymax costume serves as the robotic skin envelope. Distributed internal ToF sensors detect whole-body contact during dynamic human–robot interaction.

Inflatable Whole-Body Robotic Skin with Internal Time-of-Flight (ToF) Depth Sensing and Kinematics-Based Point-Cloud Prediction(IROS2026) An inflatable Baymax costume serves as the robotic skin envelope. Distributed internal ToF sensors detect whole-body contact during dynamic human–robot interaction.

Ryohei Sasaki@engineer

132,025 次观看 • 2 个月前

DART: Detect Anything in Real Time Detect Anything in Real Time: Real-time object detection using frontier object detection models. Training-free framework that converts SAM3 into a real-time multi-class open-vocabulary detector. Achieves 55.8 AP on COCO val2017 (80 classes) at 15.8 FPS (4 classes, 1008px) on a single RTX 4080.

DART: Detect Anything in Real Time Detect Anything in Real Time: Real-time object detection using frontier object detection models. Training-free framework that converts SAM3 into a real-time multi-class open-vocabulary detector. Achieves 55.8 AP on COCO val2017 (80 classes) at 15.8 FPS (4 classes, 1008px) on a single RTX 4080.

Ryohei Sasaki@engineer

34,632 次观看 • 1 个月前

DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors ECCV 2026 TL; DR DeWorldSG generates spatio-temporally consistent 3D semantic scene graphs from RGB-D sequences by combining depth-aware probabilistic object modeling with world-model-guided relation reasoning.

DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors ECCV 2026 TL; DR DeWorldSG generates spatio-temporally consistent 3D semantic scene graphs from RGB-D sequences by combining depth-aware probabilistic object modeling with world-model-guided relation reasoning.

Ryohei Sasaki@engineer

31,089 次观看 • 2 个月前

EgoExoMoCap: Distributed Ego-Exo Human Motion Capture ECCV 2026 (Oral) Meta Reality Labs/ETH Zürich With two or more people wearing smart glasses, EgoExoMoCap combines each wearer’s egocentric (Ego) and exocentric (Exo) views to estimate full-body motion. Without bulky multi-camera setups or mocap suits, it reconstructs 3D human motion even under occlusions using head/wrist tracking and DINOv3-based visual features.

EgoExoMoCap: Distributed Ego-Exo Human Motion Capture ECCV 2026 (Oral) Meta Reality Labs/ETH Zürich With two or more people wearing smart glasses, EgoExoMoCap combines each wearer’s egocentric (Ego) and exocentric (Exo) views to estimate full-body motion. Without bulky multi-camera setups or mocap suits, it reconstructs 3D human motion even under occlusions using head/wrist tracking and DINOv3-based visual features.

Ryohei Sasaki@engineer

26,236 次观看 • 2 个月前

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video(ECCV2026) ReViV reconstructs viewer-centric human motion (body, hand, and gaze) and view-centric scene geometry (camera and depth) from a single egocentric RGB video in a unified feed-forward model. For visualization, the initial camera pose and camera intrinsics are estimated with GeoCalib.

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video(ECCV2026) ReViV reconstructs viewer-centric human motion (body, hand, and gaze) and view-centric scene geometry (camera and depth) from a single egocentric RGB video in a unified feed-forward model. For visualization, the initial camera pose and camera intrinsics are estimated with GeoCalib.

Ryohei Sasaki@engineer

15,096 次观看 • 1 个月前

remind-reid-tracker REMIND — RE-Identification with Memory for INDoor Navigation REMIND addresses a core challenge in visual tracking: re-identifying objects that disappear and reappear, look similar to one another, or are observed from changing viewpoints. Rather than relying on position or motion cues, REMIND builds appearance-based identity models per object using DINOv3 patch features, decomposed into: Global and part-level descriptors — K-means and attention-guided semantic parts extracted per detection Relational context (neighbor sets) — structural scene layout encoded as co-occurrence graphs of neighboring objects Known-set distance disambiguation — geometry-aware resolution of visually ambiguous groups Adaptive memory — per-object appearance, part, and background models that update over time The association pipeline runs a per-frame sequence of visual evidence building, context activation, global Hungarian assignment, and post-assignment guards, producing explicit uncertainty signals (ambiguous, provisional) alongside confident identity decisions. Evaluation outputs span case, object, frame, class, scene, and batch levels, with full internal telemetry for diagnostic analysis.

remind-reid-tracker REMIND — RE-Identification with Memory for INDoor Navigation REMIND addresses a core challenge in visual tracking: re-identifying objects that disappear and reappear, look similar to one another, or are observed from changing viewpoints. Rather than relying on position or motion cues, REMIND builds appearance-based identity models per object using DINOv3 patch features, decomposed into: Global and part-level descriptors — K-means and attention-guided semantic parts extracted per detection Relational context (neighbor sets) — structural scene layout encoded as co-occurrence graphs of neighboring objects Known-set distance disambiguation — geometry-aware resolution of visually ambiguous groups Adaptive memory — per-object appearance, part, and background models that update over time The association pipeline runs a per-frame sequence of visual evidence building, context activation, global Hungarian assignment, and post-assignment guards, producing explicit uncertainty signals (ambiguous, provisional) alongside confident identity decisions. Evaluation outputs span case, object, frame, class, scene, and batch levels, with full internal telemetry for diagnostic analysis.

Ryohei Sasaki@engineer

19,013 次观看 • 2 个月前

Glob3R: Global Structure-from-Motion With 3D Foundation Models HKUST Spatial Artificial Intelligence Lab · Alibaba Group · Nanjin University · Fudan University Glob3R is a scalable global 3D reconstruction framework built on geometric foundation models. It converts dense feed-forward predictions into reliable multi-view tracks and jointly refines camera poses and scene geometry through motion averaging and bundle adjustment. Glob3R improves reconstruction accuracy and consistency on long sequences, large-scale scenes, and unordered image collections.

Glob3R: Global Structure-from-Motion With 3D Foundation Models HKUST Spatial Artificial Intelligence Lab · Alibaba Group · Nanjin University · Fudan University Glob3R is a scalable global 3D reconstruction framework built on geometric foundation models. It converts dense feed-forward predictions into reliable multi-view tracks and jointly refines camera poses and scene geometry through motion averaging and bundle adjustment. Glob3R improves reconstruction accuracy and consistency on long sequences, large-scale scenes, and unordered image collections.

Ryohei Sasaki@engineer

18,119 次观看 • 2 个月前

CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting CLM trains a 102-million Gaussian model on the MatrixCity BigCity Aerial Dataset under 4 hours using a single RTX 4090, achieving a PSNR of 25.

CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting CLM trains a 102-million Gaussian model on the MatrixCity BigCity Aerial Dataset under 4 hours using a single RTX 4090, achieving a PSNR of 25.

Ryohei Sasaki@engineer

34,570 次观看 • 9 个月前

LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM LEGO-SLAM running at 15 FPS on a ScanNet scene with language-based loop closing for drift correction. LEGO-SLAM is a 3DGS-based SLAM framework that supports open-vocabulary semantic querying and rendering. It tracks via G-ICP and efficiently builds a map by embedding Gaussians with scene-adaptive 16D language features. Map management is achieved through Language Pruning and Language-Based Loop Detection. The generated map enables open-vocabulary 3D Object Localization.

LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM LEGO-SLAM running at 15 FPS on a ScanNet scene with language-based loop closing for drift correction. LEGO-SLAM is a 3DGS-based SLAM framework that supports open-vocabulary semantic querying and rendering. It tracks via G-ICP and efficiently builds a map by embedding Gaussians with scene-adaptive 16D language features. Map management is achieved through Language Pruning and Language-Based Loop Detection. The generated map enables open-vocabulary 3D Object Localization.

Ryohei Sasaki@engineer

15,060 次观看 • 7 个月前

VLAExplain — Interpreting Vision-Language-Action (VLA) Models VLAExplain is an interpretability toolkit designed to help users visually understand the inner workings of Vision-Language-Action (VLA) models. Currently, attention analysis is supported for both the pi05 and unifolm-vla models. For details, please check pi05 and UnifoLM-VLA readme files respectively. Demo of pi05 in action:

VLAExplain — Interpreting Vision-Language-Action (VLA) Models VLAExplain is an interpretability toolkit designed to help users visually understand the inner workings of Vision-Language-Action (VLA) models. Currently, attention analysis is supported for both the pi05 and unifolm-vla models. For details, please check pi05 and UnifoLM-VLA readme files respectively. Demo of pi05 in action:

Ryohei Sasaki@engineer

12,774 次观看 • 5 个月前

TURTLMap: Real-time Localization and Dense Mapping of Low-texture Underwater Environments with a Low-cost Unmanned Underwater Vehicle

TURTLMap: Real-time Localization and Dense Mapping of Low-texture Underwater Environments with a Low-cost Unmanned Underwater Vehicle

Ryohei Sasaki@engineer

18,009 次观看 • 2 年前

LMDrive Closed-Loop End-to-End Driving with LLM An end-to-end, closed-loop, language-based autonomous driving framework, which interacts with the dynamic environment via multi-modal multi-view sensor data and natural language instructions

LMDrive Closed-Loop End-to-End Driving with LLM An end-to-end, closed-loop, language-based autonomous driving framework, which interacts with the dynamic environment via multi-modal multi-view sensor data and natural language instructions

Ryohei Sasaki@engineer

10,126 次观看 • 2 年前

没有更多内容可加载