Chongjie(CJ) Ye
@ychngji6
Followers
2K
Following
876
Media
44
Statuses
358
Ph.D. student Supervised by Prof. Xiaoguang Han
Joined November 2022
Hi3DGen has been accepted to #ICCV2025. See you all in Hawaii !🌴🥥.
Excited to announce Hi👋3DGen v0.1 - my first 3D generation project! Released at Huge thanks to the teams of @DeemosTech, @VastAIResearch, and @BytedanceTalk for their guidance. We sincerely believe open collaboration drives AI innovation forward!
3
15
136
RT @liuziwei7: 🔥1-min Interactive Video Generation with Multimodal Control🔥. Towards *long-context world model*, #LongVie is an end-to-end….
0
34
0
RT @KIRI_Engine_App: Splats in style!. After getting initial camera positions and sparse point cloud - you can swap the 'normal' input imag….
0
2
0
RT @ruilong_li: Glad to see gsplat powering real-time physics simulation together with NVIDIA Warp!. Learn more 👉
developer.nvidia.com
This post explores a promising direction for building dynamic digital representations of the physical world, a topic gaining increasing attention in recent research. We introduce an approach for…
0
9
0
RT @songyoupeng: Can we leverage the feedforward 3DGS to improve 3D VQA in LLM, even WITHOUT any supervision labels? Check out our SplatTal….
0
2
0
Our implementation integrates panorama lifting, anchor view synthesis, and inpainting into scene-based Gaussian splats, then leveraging.@theworldlabs’ frontend renderer as spatial memory to ensure long-term consistency in video generation.
0
1
3
🎮 Genie3 looks amazing but we can't play it yet! 😭 So we made our own version - and it's super fun to play!. Thanks @theworldlabs for providing the interactive frontend renderer & @DeemosTech for the awesome environment map generation!. #Genie3 #aigc
At @theworldlabs, we built a new Gaussian splatting web renderer with all the bells and whistles we needed to make splats a first-class citizen of the incredible @threejs ecosystem. Today, we're open sourcing Forge under the MIT license.
6
15
137
RT @coolboywzy: So excited to share Qwen-Image—a 20B MMDiT model! 🚀. It’s been amazing to watch its accurate text rendering start emerging….
0
5
0
RT @DeemosTech: Generate to Part ➡️ #3D Printing ➡️ Assembling in the real world 🤯.#Rodin Gen-2 makes the whole process remarkably simple.….
0
18
0
RT @Almorgand: "Dens3R: A Foundation Model for 3D Geometry Prediction". TL;DR: feed-forward visual foundation; unposed images input for hig….
0
5
0
RT @XihuiLiu: Big thanks to @_akhaliq for featuring our work!. Glad to share that GameFactory is accepted by #ICCV25 as Highlight Presentat….
github.com
[ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos - KwaiVGI/GameFactory
0
24
0
RT @taziku_co: これはクリエイターのための3D生成AIツールだ。. BANGは3DモデルをBBoxやSurface Point、さらにはテキスト入力で自在にパーツ分割可能。. 「コントロールは創造の起点」いう思想が全体に貫かれている。.via：@DeemosTec….
0
13
0
RT @Haoyang1i: Modeling the complex 3D dynamics of deformable objects is a critical challenge in robotics. How can we achieve accurate long….
0
29
0
Excited to share that our RGB-D version of OnePoseViaGen has been accepted to #CoRL2025 with three strong accepts! 🤖 Code coming soon at 6D pose estimation is crucial for robotics, but generalizing to generated objects remains challenging. We introduce
🚀We are thrilled to release an alpha version of OnePoseViaGen - a system for Panoptic 4D Scene Reconstruction from RGB video!. 👉Try it at : #AI #3D #GenerativeAI
2
11
91