📊 概要

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。

カテゴリ 件数 割合
🏗️ 3D再構成・SLAM 12 ██████████ 60%
🚗 自動運転 1 █ 5%
🤖 ロボティクス 1 █ 5%
🧠 VLA・Foundation Model 2 ██ 10%
🔧 OSS・ツール 1 █ 5%
💬 その他 3 ██ 15%

🏆 人気トップ3

🥇 1位

tweet image

   
RT 32
Like 278
Views 16000

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

tweet image

   
RT 30
Like 178
Views 11000

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

tweet image

   
RT 24
Like 157
Views 10000

[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

3D再構成・SLAM

12件のポスト

🚗 自動運転

自動運転

1件のポスト

🤖 ロボティクス

ロボティクス

1件のポスト

🧠 VLA・Foundation Model

VLA・Foundation Model

2件のポスト

🔧 OSS・ツール

OSS・ツール

1件のポスト

💬 その他

3件のポスト

📋 全ポスト一覧

全20件を表示 | # | ポスト | RT | ♥ | 日付 | |--:|:-------|---:|--:|:-----| | 1 | [3D-RE-GEN 3D Reconstruction of Indoor Scenes with a Generative Framework We prop...](https://x.com/rsasaki0109/status/2006289237696741658) | 32 | 278 | 2025-12-31 | | 2 | [OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer OmniVGGT is ...](https://x.com/rsasaki0109/status/2000400424927395986) | 30 | 178 | 2025-12-15 | | 3 | [[ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Gene...](https://x.com/rsasaki0109/status/2005484629047005480) | 24 | 157 | 2025-12-29 | | 4 | [Pi-Long: Extending π3's Capabilities on Kilometer-scale with the Framework of VG...](https://x.com/rsasaki0109/status/2001050494567891026) | 17 | 143 | 2025-12-16 | | 5 | [DVGT: Driving Visual Geometry Transform DVGT, a universal visual geometry transf...](https://x.com/rsasaki0109/status/2005084949020561746) | 22 | 138 | 2025-12-28 | | 6 | [Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching Our met...](https://x.com/rsasaki0109/status/1998588491094175760) | 18 | 126 | 2025-12-10 | | 7 | [VGGT-X: When VGGT Meets Dense Novel View Synthesis VGGT-X takes dense multi-view...](https://x.com/rsasaki0109/status/2000663920546341232) | 20 | 125 | 2025-12-15 | | 8 | [Dataset release for RA-L 2025 paper "Towards Degradation-Robust High-Precision M...](https://x.com/rsasaki0109/status/2000003494913429549) | 24 | 123 | 2025-12-14 | | 9 | [StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in...](https://x.com/rsasaki0109/status/2004386687393091907) | 19 | 116 | 2025-12-26 | | 10 | [[AUTCON'25] BIMNet: Dataset and benchmark for as-built BIM reconstruction from r...](https://x.com/rsasaki0109/status/2005800420577526254) | 24 | 113 | 2025-12-30 | | 11 | [Co-Me: Confidence Guided Token Merging for Visual Geometric Transformers](https://x.com/rsasaki0109/status/2003299526845825130) | 12 | 99 | 2025-12-23 | | 12 | [E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training](https://x.com/rsasaki0109/status/2004695846965968932) | 14 | 89 | 2025-12-26 | | 13 | [[NeurIPS 2025] SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Und...](https://x.com/rsasaki0109/status/1999281961018490945) | 13 | 88 | 2025-12-12 | | 14 | [[AAAI 2025] Offical implementation of "DrivingForward: Feed-forward 3D Gaussian ...](https://x.com/rsasaki0109/status/1999585050904658194) | 16 | 87 | 2025-12-12 | | 15 | [[RA-L'25 & IROS'25] II-NVM: Enhancing Map Accuracy and Consistency with Normal V...](https://x.com/rsasaki0109/status/2004024302891642986) | 9 | 76 | 2025-12-25 | | 16 | [[CVPR 2025] DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided ...](https://x.com/rsasaki0109/status/2003661924949447109) | 13 | 64 | 2025-12-24 | | 17 | [StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modelin...](https://x.com/rsasaki0109/status/1998179880421433754) | 6 | 44 | 2025-12-08 | | 18 | [nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (...](https://x.com/rsasaki0109/status/1998860273734881508) | 5 | 30 | 2025-12-10 | | 19 | [名古屋にSEQSENSEの警備ロボットいた!](https://x.com/rsasaki0109/status/1999701889999638945) | 0 | 13 | 2025-12-13 | | 20 | [新幹線間違えて母校最寄りで降りてしまった](https://x.com/rsasaki0109/status/2006187895548498194) | 0 | 1 | 2025-12-31 |