35件のポスト（リプライ除く）を7カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

Describe Anything, Anywhere, at Any Moment DAAAM builds a hierarchical 4D scene graph as spatio-temporal memory, enabling embodied agents to describe anything, anywhere, at any moment.

🔗 ポストを見る

🥈 2位

supersplat 3D Gaussian Splat Editor The SuperSplat Editor is a free and open source tool for inspecting, editing, optimizing and publishing 3D Gaussian Splats. It is built on web technologies and runs in the browser, so there’s nothing to download or

🔗 ポストを見る

🥉 3位

SiMpLE A simple LiDAR odometry method reducing the complexity and configuration burden of localization algorithms.

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

11件のポスト

supersplat 3D Gaussian Splat Editor The SuperSplat Editor is a free and open source tool for inspecting, editing, optimizing and publishing 3D Gaussia... (♥ 240)

• SiMpLE A simple LiDAR odometry method reducing the complexity and configuration burden of localization algorithms. (♥ 214)

LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM LEGO-SLAM running at 15 FPS on a ScanNet scene with language-based loop closing for drift corr... (♥ 208)

maplibre-gl-lidar A MapLibre GL JS plugin for visualizing LiDAR point clouds using deck gl. Features - Load and visualize LAS/LAZ/COPC point cloud fil... (♥ 184)

Global-LVBA Global LiDAR-Visual Bundle Adjustment Global-LVBA is a globally consistent LiDAR–Visual Bundle Adjustment system for refinement after LiDA... (♥ 123)

🚗 自動運転

3件のポスト

SfmPanOcc Vision-Based Panoptic Occupancy Prediction in Urban Environments (♥ 86)

[ICRA 2026] StepNav: Efficient Planning with Structured Trajectory Priors We present StepNav, an efficient planning framework for visual navigation th... (♥ 78)

• drawtonomy Whiteboard for Driving Diagrams 🚗 Intuitively place lanes, vehicles, pedestrians, and traffic lights. Browser-based. For autonomous driving… (♥ 19)

🤖 ロボティクス

1件のポスト

rust_roboticsもgithub ioで紹介ページ作った rust_robotics Rust implementation of PythonRobotics, sample codes for robotics algorithms (♥ 66)

🧠 VLA・Foundation Model

3件のポスト

Describe Anything, Anywhere, at Any Moment DAAAM builds a hierarchical 4D scene graph as spatio-temporal memory, enabling embodied agents to describe ... (♥ 484)

• ACG: Action Coherence Guidance for Flow-based Vision-Language-Action Models (ICRA 2026) Action Coherence Guidance (ACG) is a training-free, test-time … (♥ 120)
• VLAExplain — Interpreting Vision-Language-Action (VLA) Models VLAExplain is an interpretability toolkit designed to help users visually understand the… (♥ 112)

📄 論文紹介

2件のポスト

City2Graph: GeoAI with Graph Neural Networks (GNNs) and Spatial Network Analysis -Graph Construction for GeoAI: Build graphs from diverse urban datase... (♥ 58)

Do Visual Imaginations Improve Vision-and-Language Navigation Agents? Vision-and-Language Navigation (VLN) agents are tasked with navigating an unseen... (♥ 26)

🔧 OSS・ツール

4件のポスト

• 今のロボティクス系ossの新潮流ってなんやろ (♥ 19)
• もうちょい世間のオープンソース活動を推進したくなってきたな (♥ 12)

初めてGithubで詐欺メンションが来た 最近各種SNSでこういうの多いなぁ (♥ 3)

• もうちょっとoss紹介にひとひねりいれるかぁ (♥ 2)

💬 その他

11件のポスト

自分のHomepageを作った。 (♥ 34)

MapTrace: A 2M-Sample Synthetic Dataset for Wayfinding Path Tracing This repository contains the dataset and code for MapTrace, a large-scale syntheti... (♥ 20)

←AIコーディングしてる時の自分の自認 →強強プログラマーのAIコーディング (♥ 17)

• 現代の入社における技術試験ってコーディングテストよりも設計テストの方が良くないと思ったけど、評価が難しいからすぐには導入できないか そこらへんの評価をある程度自動化するAIを作ったら売れそう (♥ 8)
• おおー 👀 三菱電機が50億円出資したAIスタートアップ「燈」CEOを直撃！東大・松尾研発の「隠れユニコーン」の正体とは？創業期から黒字、エンジニアの4割が東大出身、原則フル出社《再配信》 2026年3月3日 (♥ 6)

📋 全ポスト一覧

20件のポスト（リプライ除く）を5カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

EgoX: Egocentric Video Generation from a Single Exocentric Video

🔗 ポストを見る

🥈 2位

insight-sam3 Uses SAM3 to transfer 2D semantics onto 3D point clouds, producing segmented training data and efficient scene graphs for indoor environments.

🔗 ポストを見る

🥉 3位

Paper2Rebuttal RebuttalAgent: AI-Powered Academic Paper Rebuttal Assistant RebuttalAgent is an AI-powered multi-agent system that helps researchers craft high-quality rebuttals for academic paper reviews. The system analyzes reviewer comments, search…

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

8件のポスト

insight-sam3 Uses SAM3 to transfer 2D semantics onto 3D point clouds, producing segmented training data and efficient scene graphs for indoor environm... (♥ 468)

[ICLR 2026] FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction FantasyWorld is a unified feed-forward model for join... (♥ 235)

• Pixie: Physics from Pixels Feed-forward model for predicting 3D physics with 3DGS + NeRF Photorealistic 3D reconstructions (NeRF, Gaussian Splatting) … (♥ 227)

[SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction Our ... (♥ 115)

3D Diffusion Policy Generalizable Visuomotor Policy Learning via Simple 3D Representations 3D Diffusion Policy (DP3) is a universal visual imitation l... (♥ 95)

🤖 ロボティクス

1件のポスト

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance We present our NeurIPS 2025 paper Wan-Move, a simple and ... (♥ 73)

🧠 VLA・Foundation Model

5件のポスト

• ACG: Action Coherence Guidance for Flow-based VLA Models (ICRA 2026) Action Coherence Guidance (ACG) is a training-free, test-time guidance algorithm … (♥ 132)

PlantInstGen Tailored Refinement of Vision-Language Models for Plant Instance Segmentation (♥ 58)

VLG-Loc Vision-Language Global Localization (VLG-Loc) is a global localization method that uses camera images and a human-readable labeled footprint m... (♥ 48)

MindDrive: A Vision-Language-Action Model for Autonomous Driving Utilizing Language as Action in Online Reinforcement Learning Current Vision-Language... (♥ 43)

dVoting: Fast Voting for dLLMs Abstract Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling, offering comp... (♥ 8)

📄 論文紹介

3件のポスト

• Paper2Rebuttal RebuttalAgent: AI-Powered Academic Paper Rebuttal Assistant RebuttalAgent is an AI-powered multi-agent system that helps researchers cr… (♥ 306)
• InstantSfM: Fully Sparse and Parallel Structure-from-Motion TLDR: InstantSfM is a fully sparse and parallel Structure-from-Motion pipeline that levera… (♥ 212)

SciencePlots Matplotlib styles for scientific plotting This repo has Matplotlib styles to format your figures for scientific papers, presentations and... (♥ 21)

💬 その他

3件のポスト

• EgoX: Egocentric Video Generation from a Single Exocentric Video (♥ 852)

imap High-resolution map (OpenDrive\Apollo) visualization and conversion tools imap is a tool for visualize and convert format of the hd-map. This pro... (♥ 17)

• AIで並列タスクこなしてると、FFのアクティブタイムバトル（ATB）してる気分になる (♥ 5)

📋 全ポスト一覧

20件のポスト（リプライ除く）を6カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

SpatialLLM：Enhancing Large Language Models for Urban Spatial Intelligence SpatialLLM is a comprehensive framework for enhancing Large Language Models with urban spatial understanding capabilities. This project integrates point cloud processing,

🔗 ポストを見る

🥈 2位

OpenNavMap Structure-Free Topometric Mapping via Large-Scale Collaborative Localization OpenNavMap is a lightweight, structure-free topometric mapping system that enables large-scale collaborative localization across multiple sessions without requiri…

🔗 ポストを見る

🥉 3位

openvps Open Visual Positioning Service

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

10件のポスト

OpenNavMap Structure-Free Topometric Mapping via Large-Scale Collaborative Localization OpenNavMap is a lightweight, structure-free topometric mapping... (♥ 276)

Concerto [NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations TL;DR: This repo provide j... (♥ 192)

• CuMesh: High-Performance Geometry Processing for PyTorch Cuda mesh utils. CuMesh is a GPU-accelerated library designed for high-performance 3D geometr… (♥ 183)

IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction Humans naturally perceive both geometric structure and semantic content of... (♥ 172)

Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework Diffusion-based 3D generation pipelines share a common ... (♥ 158)

🚗 自動運転

2件のポスト

• alpamayo-autoware Alpamayo ROS 2 Node Usage Guide (♥ 174)
• BEV (♥ 2)

🤖 ロボティクス

3件のポスト

Primitive_Planner Primitive-Swarm: An Ultra-lightweight and Scalable Planner for Large-scale Aerial Swarms (♥ 77)

Open Duck Mini v2 Making a mini version of the BDX droid > We are making a miniature version of the BDX Droid by Disney. It is about 42 centimeters ta... (♥ 33)

• toio_gazebo This is a ROS 2 Package to develop package of toio using Gazebo. (♥ 21)

🧠 VLA・Foundation Model

2件のポスト

SpatialLLM：Enhancing Large Language Models for Urban Spatial Intelligence SpatialLLM is a comprehensive framework for enhancing Large Language Models ... (♥ 400)

hn-time-capsule Analyzing Hacker News discussions from a decade ago in hindsight with LLMs A Hacker News time capsule project that pulls the HN frontp... (♥ 3)

📄 論文紹介

1件のポスト

• [RA-L 26] Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation (♥ 116)

💬 その他

2件のポスト

openvps Open Visual Positioning Service (♥ 250)

• メイカーフェアに興味が出てきた (♥ 5)

📋 全ポスト一覧

20件のポスト（リプライ除く）を6カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

3D-RE-GEN 3D Reconstruction of Indoor Scenes with a Generative Framework We propose single-image 3D scene reconstruction for producing complete, editable scenes from a single photograph. Our method reconstructs individual objects and the surrounding

🔗 ポストを見る

🥈 2位

OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer OmniVGGT is a spatial foundation model that can effectively benefit from an arbitrary number of auxiliary geometric modalities (depth, camera intrinsics and pose) to obtain high-qual…

🔗 ポストを見る

🥉 3位

[ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models InfiniCube take advantage of recent advances in 3D and video generative models to achieve large dynamic scene generation with flexib…

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

12件のポスト

3D-RE-GEN 3D Reconstruction of Indoor Scenes with a Generative Framework We propose single-image 3D scene reconstruction for producing complete, edita... (♥ 278)

[ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models InfiniCube take advantage of rec... (♥ 157)

DVGT: Driving Visual Geometry Transform DVGT, a universal visual geometry transformer for autonomous driving, directly predicts metric-scaled global 3... (♥ 138)

Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching Our method for scalable multi-view point cloud registration. To register mult... (♥ 126)

VGGT-X: When VGGT Meets Dense Novel View Synthesis VGGT-X takes dense multi-view images as input. It first uses memory-efficient VGGT to losslessly pr... (♥ 125)

🚗 自動運転

1件のポスト

[NeurIPS 2025] SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding Existing LiDAR generative models are limited to producing u... (♥ 88)

🤖 ロボティクス

1件のポスト

名古屋にSEQSENSEの警備ロボットいた！ (♥ 13)

🧠 VLA・Foundation Model

2件のポスト

OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer OmniVGGT is a spatial foundation model that can effectively benefit from an arbitr... (♥ 178)

• StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling StreamVLN generates action outputs from continuous video input in an… (♥ 44)

🔧 OSS・ツール

1件のポスト

Pi-Long: Extending π3's Capabilities on Kilometer-scale with the Framework of VGGT-Long (♥ 143)

💬 その他

3件のポスト

Co-Me: Confidence Guided Token Merging for Visual Geometric Transformers (♥ 99)

nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO) (♥ 30)

• 新幹線間違えて母校最寄りで降りてしまった (♥ 1)

📋 全ポスト一覧

20件のポスト（リプライ除く）を4カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

[CVPR 2025 Highlight] SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos SLAM3R is a real-time dense scene reconstruction system that regresses 3D points from video frames using feed-forward neural networks, without explicitly

🔗 ポストを見る

🥈 2位

[RA-L 2025] ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting ActiveSplat enables the agent to explore the environment autonomously to build a 3D map on the fly. The integration of a Gaussian map and a Voronoi graph as…

🔗 ポストを見る

🥉 3位

NavMap NavMap is an open-source C++ and ROS 2 library for representing navigable surfaces for mobile robot navigation and localization. Unlike classic grid-based maps, NavMap stores the environment as triangular meshes (NavCels), enabling efficient q…

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

14件のポスト

• [CVPR 2025 Highlight] SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos SLAM3R is a real-time dense scene reconstruction system t… (♥ 416)
• [RA-L 2025] ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting ActiveSplat enables the agent to explore the environment… (♥ 316)

NavMap NavMap is an open-source C++ and ROS 2 library for representing navigable surfaces for mobile robot navigation and localization. Unlike classic... (♥ 224)

Official implementation of "S2M2: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025" (♥ 211)

LightGlueStick a Fast and Robust Glue for Joint Point-Line Matching LightGlueStick adaptively adjusts its depth based on image difficulty, exiting aft... (♥ 147)

🚗 自動運転

2件のポスト

form FORM is a LiDAR Odometry system that performs fixed-lag smoothing and sub-map reparations, all in real-time with minimal parameters. (♥ 113)

[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences (♥ 63)

🤖 ロボティクス

3件のポスト

PHUMA: Physically-Grounded Humanoid Locomotion Dataset (♥ 129)

TAVP Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation TVVE employs an efficient exploration policy (MVEP), accele... (♥ 55)

• lwrclpy-for-FastDDSv3 An rclpy-compatible Python library built directly on Fast DDS v3—designed to solve the friction of using ROS 2 with Python ML/AI… (♥ 27)

📄 論文紹介

1件のポスト

[arXiv 2025] Generative View Stitching This is the official repository for the paper Generative View Stitching (GVS), which enables collision-free cam... (♥ 70)

📋 全ポスト一覧

17件のポスト（リプライ除く）を4カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

TTT3R: 3D Reconstruction as Test-Time Training TL;DR: A simple state update rule to enhance length generalization for CUT3R.

🔗 ポストを見る

🥈 2位

[NeurIPS 2025] Pixel-Perfect Depth This work presents Pixel-Perfect Depth, a monocular depth estimation model with pixel-space diffusion transformers. Compared to existing discriminative and generative models, its estimated depth maps can produce

🔗 ポストを見る

🥉 3位

Trace Anything: Representing Any Video in 4D via Trajectory Fields

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

10件のポスト

• TTT3R: 3D Reconstruction as Test-Time Training TL;DR: A simple state update rule to enhance length generalization for CUT3R. (♥ 203)

[NeurIPS 2025] Pixel-Perfect Depth This work presents Pixel-Perfect Depth, a monocular depth estimation model with pixel-space diffusion transformers.... (♥ 194)

[AAAI 2025 Oral] FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation (♥ 131)

LiteVLoc: Map-Lite Visual Localization for Image-Goal Navigation (ICRA2025) LiteVLoc is a hierarchical visual localization framework designed to enabl... (♥ 113)

• USplat4D: Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction (♥ 100)

🚗 自動運転

2件のポスト

autonomous-valet-parking Framework for Autonomous Valet Parking (AVP) with Autoware. Combines a YOLO detection server, Unity parking spot scripts, and... (♥ 137)

visibility_rrt The Visibility-Aware RRT* implementation for safety-critical navigation with perception-limited robots.[RA-L 2025] (♥ 63)

🤖 ロボティクス

1件のポスト

[IEEE RA-L] Air-IO: a learning-based IO framework targeted for UAV (♥ 15)

💬 その他

4件のポスト

Trace Anything: Representing Any Video in 4D via Trajectory Fields (♥ 191)

online_adaptive_cbf Implementation of the Online Adaptive CBF(Cost Barrier Function) for safety-critical navigation for input constrained systems. (♥ 47)

Fast-ShapeAndPose Shape and pose estimation via eigenproblem with eigenvector nonlinearities. Category-Level Shape and Pose Estimation in Less Than a ... (♥ 38)

• 国際学会の時期になるとフォロワー数が伸びる (♥ 2)

📋 全ポスト一覧

20件のポスト（リプライ除く）を5カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

[NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO

🔗 ポストを見る

🥈 2位

RKO_LIO - LiDAR-Inertial Odometry Without Sensor-Specific Modelling Four different platforms, four different environments, one odometry system

🔗 ポストを見る

🥉 3位

[CVPR 25] Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation Vid2Sim is a novel framework that converts monocular videos into photorealistic and physically interactive simulation environments for training embodied agents wi…

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

10件のポスト

MapAnything: Universal Feed-Forward Metric 3D Reconstruction Meta/Carnegie Mellon University MapAnything is a simple, end-to-end trained transformer m... (♥ 225)

• ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association ViSTA-SLAM is a real-time monocular dense SLAM pipeline that combines a Symmetric Two-view… (♥ 180)
• ORB-SLAM-Python ORB_SLAM3 Python Bindings (♥ 155)
• [CoRL 2025] ActLoc: Learning to Localize on the Move via Active Viewpoint Selection > We present ActLoc, a learning-based approach for active viewpoin… (♥ 150)

Rohbau3D A Shell Construction Site 3D Point Cloud Dataset > We introduce Rohbau3D, a novel dataset of 3D point clouds that realistically represent ind... (♥ 134)

🚗 自動運転

4件のポスト

RKO_LIO - LiDAR-Inertial Odometry Without Sensor-Specific Modelling Four different platforms, four different environments, one odometry system (♥ 395)

• DWPP: Dynamic Window Pure Pursuit for Robot Path Tracking Considering Velocity and Acceleration Constraints (♥ 41)
• gnss-lidar-dataprocessing Processes gnss/lidar data from raw files PCAP conversion files (PCAPtoROS) can be built in a ros2 workspace. You can just pu… (♥ 26)

FAPP [T-RO'24] Fast and Adaptive Perception and Planning for UAVs in Dynamic Cluttered Environments (♥ 20)

🤖 ロボティクス

2件のポスト

learn-to-calibrate [IROS2025] The World's First RL-based Sensor Calibration Method: A Targetless, User-friendly, and Robust Approach. L2Calib: SE(3)-M... (♥ 68)

• dora-rs DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications…. (♥ 26)

🧠 VLA・Foundation Model

1件のポスト

[CVPR 25] Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation Vid2Sim is a novel framework that converts monocular videos in... (♥ 257)

📄 論文紹介

3件のポスト

[NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO (♥ 533)

• [NeurIPS 2025 (Spotlight)] The implementation for the paper “4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos” (♥ 224)
• Awesome-Image-Matching Bibliographic list for papers of image matching (♥ 48)

📋 全ポスト一覧

19件のポスト（リプライ除く）を7カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

[ICRA’25] One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation

🔗 ポストを見る

🥈 2位

[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

🔗 ポストを見る

🥉 3位

[ICCV 2025] This is the official implementation of POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

8件のポスト

[ICRA'25] One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation (♥ 223)

[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering (♥ 169)

[ICCV 2025] This is the official implementation of POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction (♥ 148)

• Awesome-Transformer-based-SLAM Paper Survey for Transformer-based SLAM (♥ 136)

ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary (♥ 89)

🚗 自動運転

2件のポスト

CogniPlan: Uncertainty-Guided Path Planning with Conditional Generative Layout Prediction TL;DR CogniPlan is a path planning framework that leverages ... (♥ 85)

• autoware.privately-owned-vehicles An open-source autonomous highway pilot system for privately owned vehicles (♥ 12)

🤖 ロボティクス

2件のポスト

BotVIO: A Lightweight Transformer-Based Visual-Inertial Odometry for Robotics (♥ 118)

minecraft_ros2 ros2 minecraft mod (♥ 44)

🧠 VLA・Foundation Model

2件のポスト

ICCV 2025 | TesserAct: Learning 4D Embodied World Models (♥ 16)

LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models (♥ 9)

📄 論文紹介

2件のポスト

STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes (♥ 75)

Proteina: Scaling Flow-based Protein Structure Generative Models (ICLR 2025 Oral Paper) Proteina is a new large-scale flow-based protein backbone gene... (♥ 11)

🔧 OSS・ツール

1件のポスト

• Githubのデフォルトアイコンに謎の愛着があって他でも使ってたんだけど、抽象的で覚えづらいから他のアイコンに変えたいんだけど案が無い (♥ 0)

💬 その他

2件のポスト

• 自分の中の価値観を考えてたんだけど、下記になった ・win-win ・よく考え、すぐ行動 (♥ 13)
• 自分のXアカウントの背景を考えてるんだけど、近場でマルチパスが発生しやすい環境の写真でも取るか (♥ 2)

📋 全ポスト一覧

20件のポスト（リプライ除く）を6カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

ROMAN(Robust Object Map Alignment Anywhere) a view-invariant global localization method that maps open-set objects and uses the geometry, shape, and semantics of objects to find the transformation between a current pose and previously created object …

🔗 ポストを見る

🥈 2位

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

🔗 ポストを見る

🥉 3位

Dens3R: A Foundation Model for 3D Geometry Prediction > Dens3R is a feed-forward visual foundation model that takes unposed images as input and outputs high-quality 3D pointmap with unified geometric dense prediction.

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

8件のポスト

ROMAN(Robust Object Map Alignment Anywhere) a view-invariant global localization method that maps open-set objects and uses the geometry, shape, and s... (♥ 241)

• VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold (♥ 205)

GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats (♥ 152)

• [ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy > SpatialTrackerV2 is the first unified, end-to-end 3D point tracking model which estimates … (♥ 128)
• awesome-3d-point-cloud-denoising A curated list of awesome 3D point cloud denoising papers (♥ 93)

🚗 自動運転

3件のポスト

• Autoware Diffusion Planner > It leverages the Diffusion Planner model, as described in the paper “Diffusion-Based Planning for Autonomous Driving with… (♥ 152)

[IEEE RAL'25 & IROS'25] UA-MPC: Uncertainty-Aware Model Predictive Control for Motorized LiDAR Odometry (♥ 121)

BEV-LIO-LC BEV Image Assisted LiDAR-Inertial Odometry with Loop Closure(IROS 2025) (♥ 7)

🤖 ロボティクス

1件のポスト

• astroviz ROS2 package implementing a teleoperation interface using QT (♥ 23)

🧠 VLA・Foundation Model

3件のポスト

Dens3R: A Foundation Model for 3D Geometry Prediction > Dens3R is a feed-forward visual foundation model that takes unposed images as input and output... (♥ 195)

VFM-Registration LiDAR Registration with Visual Foundation Models (♥ 38)

[IROS'25 Oral] WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation (♥ 6)

📄 論文紹介

1件のポスト

[CVPR 2025] MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation Distillation (♥ 84)

💬 その他

4件のポスト

VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences (♥ 174)

π³: Scalable Permutation-Equivariant Visual Geometry Learning π³ reconstructs visual geometry without a fixed reference view, achieving robust, state-... (♥ 95)

StreamVGGT Streaming 4D Visual Geometry Transformer (♥ 60)

• 久しぶりに日本語記事書くモチベが出てきたんだけど、どこで書こうかな (♥ 2)

📋 全ポスト一覧

15件のポスト（リプライ除く）を4カテゴリに分類しました。

🏆 人気トップ3

🥇 1位

NVlabs/PyCuVSLAM Highly accurate and efficient VSLAM system for Python > PyCuVSLAM is the official Python wrapper around the cuVSLAM visual-inertial SLAM (Simultaneous Localization And Mapping) software package developed by NVIDIA. It is a highly acc…

🔗 ポストを見る

🥈 2位

ICRA2025: OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding

🔗 ポストを見る

🥉 3位

Splat-LOAM 2D Gaussian Splatting based LiDAR Odometry And Mapping

🔗 ポストを見る

📂 カテゴリ別ハイライト

🏗️ 3D再構成・SLAM

7件のポスト

ICRA2025: OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding (♥ 256)

• Splat-LOAM 2D Gaussian Splatting based LiDAR Odometry And Mapping (♥ 166)

DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes >DualMap is an online open-vocabulary mapp... (♥ 123)

Test3R: Learning to Reconstruct 3D at Test Time (♥ 84)

MISO: Multiresolution Submap Optimization for Efficient Globally Consistent Neural Implicit Reconstruction(RSS'25) (♥ 77)

🤖 ロボティクス

3件のポスト

The CU-Multi Dataset CU-MULTI is a multi-robot dataset that contains two large-scale outdoor sequences collected by a single ground robot on The Unive... (♥ 101)

• [RSS 2025] Learning Getting-Up Policies for Real-World Humanoid Robots (♥ 20)

arp Autoregressive Policy for Robot Learning (RA-L 2025) Action Sequence Learning for Robotic Manipulation (♥ 6)

🧠 VLA・Foundation Model

2件のポスト

• NVlabs/PyCuVSLAM Highly accurate and efficient VSLAM system for Python > PyCuVSLAM is the official Python wrapper around the cuVSLAM visual-inertial S… (♥ 304)

Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning (♥ 11)

💬 その他

3件のポスト

• パーティクルフィルタの可能性について考えてたんだけど、計算量爆発してダメだった (♥ 7)

お人よしな経営初心者あっておもろい いっぱい失敗して成長して欲しい (♥ 3)

• 万博行きたくなってきたな 10月13日までか (♥ 3)

📋 全ポスト一覧