Toshiya Yura (@toshiya427) 's Twitter Profile
Toshiya Yura

@toshiya427

Computer Vision Engineer. Recently 3D Vision. Graduated @TohokuUniPR. Visited @UofT. Research/Software Engineer @Sony.

ID: 1163451812323586056

calendar_today19-08-2019 14:05:12

163 Tweet

89 Followers

218 Following

Igor Gilitschenski (@igilitschenski) 's Twitter Profile Photo

Excited to share our #CVPR2024 work (oral & award candidate) on integrating map uncertainty into trajectory prediction led by Xunjiang Gu. Our key insight is simple: Scene uncertainties matter for agent trajectories. 🧵1/n

Excited to share our #CVPR2024 work (oral &amp; award candidate) on integrating map uncertainty into trajectory prediction led by <a href="/XunjiangGu/">Xunjiang Gu</a>.

Our key insight is simple: Scene uncertainties matter for agent trajectories. 🧵1/n
Thomas Kipf (@tkipf) 's Twitter Profile Photo

Excited to share our work on Neural Assets: a new method for enabling 3D asset-level control in image diffusion models – scalable & without any 3D inductive biases. Neural Assets goes beyond text or pixel-based control & provides an interface inspired by 3D graphics tools. 🧵

Igor Gilitschenski (@igilitschenski) 's Twitter Profile Photo

Check out our #CVPR2024 work on Label-efficient object detection for event cameras led by Ziyi Wu. We leverage an often neglected property of event-based detection datasets: the sparsity of their labels. 🧵1/n

Check out our #CVPR2024 work on Label-efficient object detection for event cameras led by <a href="/Dazitu_616/">Ziyi Wu</a>.

We leverage an often neglected property of event-based detection datasets: the sparsity of their labels. 🧵1/n
Igor Gilitschenski (@igilitschenski) 's Twitter Profile Photo

Happy to present our third #CVPR2024 paper, SPAD, which has been led by Yash Kant. SPAD is a 3d-multi-view image generation model that can leverage text or image inputs and generate consistent views from arbitrary camera poses. 🧵1/n

Ashkan Mirzaei (@ashmrz10) 's Twitter Profile Photo

Thanks AK for sharing our work. 🚀Have a video of an animated object (generated or not) and wish to instantly get the 4D asset out of it?🎥✨Wish no more as we propose L4GM, a large reconstruction model for 4D objects!🌟Amazing project led by Jiawei Ren at Nvidia.🏆🔍

ジリ子🇨🇦👩‍💻 (@__watz) 's Twitter Profile Photo

カナダ在住日本人向けのフリマアプリがあるみたいです!! 開発まもなくて、誤作動もあるかもしれないけど、みんなで利用してみましょう!!私も機会があったら投稿できたら嬉しいな!!

カナダ在住日本人向けのフリマアプリがあるみたいです!!

開発まもなくて、誤作動もあるかもしれないけど、みんなで利用してみましょう!!私も機会があったら投稿できたら嬉しいな!!
佐藤 竜馬 / Ryoma Sato (@joisino_) 's Twitter Profile Photo

機械学習若手の会 #YAML2024 での招待講演『研究の進め方 ランダムネスとの付き合い方について』のスライドを公開しました speakerdeck.com/joisino/random…

Ziyi Wu (@dazitu_616) 's Twitter Profile Photo

📢MinT: Temporally-Controlled Multi-Event Video Generation📢 mint-video.github.io TL;DR: We identify a fundamental failure mode of existing video generators: they cannot produce videos with sequential events. MinT unlocks this capability with temporal grounding of events. 🧵

玉木雄一郎(国民民主党) (@tamakiyuichiro) 's Twitter Profile Photo

今夏は猛暑が予想なのに政府は4月から電気代への支援をやめる。電気代高騰の原因の一つは再エネ賦課金。太陽光が一番安いと言うなら再エネ賦課金はやめたらいい。国の後押しではなく市場に任せればいい。国民民主党はまず再エネ賦課金徴収停止による電気代値下げを求めます。 nikkei.com/article/DGKKZO…

藤原 麻里菜 | Marina Fujiwara (@muda_zukuri) 's Twitter Profile Photo

高級ブランドを身につけている人間をヒエラルキーの頂点とし、忠誠心を誓うロボット犬を開発したU^ェ^U ラズパイ+AIカメラ(IMX500)で作ったよ🐶🐶

Ashkan Mirzaei (@ashmrz10) 's Twitter Profile Photo

[1/9] 🚀 We introduce 4Real-Video-V2, a method that can generate 4D scenes from a simple text prompt, viewable from any angle at any moment in time. It’s fast, photorealistic, and works on full scenes. Here's how it works and why it matters. 👇 snap-research.github.io/4Real-Video-V2/