Filter
Exclude
Time range
-
Near
snow11828147
Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image,CVPR2026 衣服のdynamicsを考慮した3D復元の研究.面白そうと思い読み始めたが,先行研究を色々調べながら読んでいたら理解するのに3日かかった・・・ juhyeon-kwon.github.io/DynaA…
1
49
Ismini_L
🤖 🧭 How does a robot know how far along it is in a long task? Most VLA policies cannot explicitly track task progress, which is why they are often brittle in long-horizon, multi-step tasks. PALM (#CVPR2026) makes the policy progress-aware, coupling future affordance prediction with continuous progress estimation in a closed loop. Our code and model checkpoints are released 👇
🤖 Code and model checkpoints are out for PALM, our #CVPR2026 work on long-horizon robot manipulation. Work led by Yuanzhe Liu @ PLAN Lab👏 🧵1/4👇
9
770
Aryan retweeted
GoogleResearch
Check out TIPSv2 at our #CVPR2026 booth kiosk at 4pm! A foundational image-text encoder with spatial awareness, leading to strong results for vision & multimodal applications. Presented by Andre Araujo, Erik de Godoy & Gabriele Berton. gdm-tipsv2.github.io/ @GoogleDeepMind
4
7
53
11,123
ctxzz
インターネットに豊富に存在するラベルなし動画から自動的に学習データを生成し、様々な3Dシーン理解(低次の知覚から高次の推論まで)を実現。生の入力を直接扱うモデルの方がスケールに強い #CVPR2026 Lifting Unlabeled Internet-level Data for 3D Scene Understanding sv-pp.github.io/
34
JY EnvironmentGeek retweeted
CalibrateVC
Calibrate investor @Katie_Calibrate’s latest Substack unpacks one of the biggest themes emerging from #CVPR2026: in robotics, looking right and being right are very different problems. The industry is starting to move past flashy, photorealistic demos and toward systems that can actually operate reliably in the real world. Her recap covers the shifting center of gravity toward physical AI, robotics memory limitations, humanoids in the home, and more: katievasquez7.substack.com/p…
1
5
106
NASNETou
A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space (CVPR2026 Oral / Award Candidate) openaccess.thecvf.com/conten… ①画像ペア→表現抽出 ②表現→画像生成 ③シード→新規表現生成による、Midjourneyライクな離散スタイルコード 画像生成CoTyleの提案
187
SeoulNatlUni
🚗 Every self-driving car faces the same question: What's the safest next move? Prof. Jun Won Choi's team at Seoul National University developed SafeDrive, a homegrown end-to-end autonomous driving AI model selected as a CVPR 2026 Highlight Paper. Instead of making a single prediction, the AI compares multiple possible driving paths and chooses the safest one—bringing autonomous driving one step closer to real roads. Read more: eng.snu.ac.kr/en/communicati… #SNUResearch #CVPR2026 #AutonomousDriving #ArtificialIntelligence #ComputerVision #PhysicalAI
1
4
209
Ziqing Shi (Seesaw) retweeted
HenghuiDing
#CVPR2026 Introducing #EffectErase. It removes both the target object and its visual effects (e.g., shadows and reflections) from a video. -Project: henghuiding.com/EffectErase/ -Paper: arxiv.org/abs/2603.19224 -Code: github.com/FudanCVL/EffectEr…
2
6
236
今野 琢磨@ソフトウェアQA/DevOps/データ分析/ちゃんと食べて痩せる🔥 retweeted
acroquest
当社のKaggle Grandmaster 山本が、世界最高峰のコンピュータービジョン国際学会「CVPR2026」に現地で参加。AI研究の最前線を直接見てきました。 現地で感じた研究発表の熱気や、Foundation Model活用の広がり、AIエージェント×動画解析の可能性についてレポートしています。 Acroquestでは、こうした最先端の技術動向をキャッチアップし、自社R&Dやお客様への提案・開発に活かしています。AI・機械学習・画像認識に関心のある方、ぜひご覧ください。 ▼記事はこちら wantedly.com/companies/acroq… #Acroquest #中途採用 #新卒採用 #エンジニア採用 #Kaggle #AIエンジニア #機械学習 #コンピュータービジョン #CVPR2026
1
8
269