Shijie Zhou
@ShijieZhoucla
Followers
137
Following
75
Media
6
Statuses
26
PhD Student @UCLA, 3D Computer Vision | Research Intern @Apple | Previously @Google @Columbia.
Joined July 2021
🚀 Our #ICCV2025 work — VLM4D is here!. The first benchmark to truly test if Vision-Language Models can think in 4D (3D space📷 + time🕒). Today’s MLLMs/VLMs can solve complex math via visual inputs… but can’t even tell left from right in a video?👀. 👉
1
4
19
RT @_akhaliq: Feature4X. Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
0
19
0
RT @janusch_patas: Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields. Contributions:.• We pro….
0
8
0
RT @rhfeiyang: Check out our demo for the Art-Free Diffusion model and the Art Adapters! 🎨✨ . .
0
1
0
RT @WayneINR: 🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing….
0
64
0
RT @_vztu: 🚨Revolutionizing 4D VR/AR Content Generation!.Excited to share our latest paper on 4K4DGen, a breakthrough in creating panoramic….
0
20
0
DreamScene360 is now open source! Visit our website for more details!. Website: Code: Unfortunately, I can't make it to #ECCV2024 in Italy🇮🇹 this year, but I've already flown around the Colosseum in my own generated metaverse 😊.
github.com
[ECCV 2024] DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting - ShijieZhou-UCLA/DreamScene360
DreamScene360. Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting. The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360^{circ} scene generation pipeline
0
1
5
Tomorrow 6/21 we will be presenting our Highlight Poster at #CVPR2024 .📌Arch 4A-E Poster #205, 10:30AM - noon. Come and say hello if you are interested! 😊.
(1/5).3D Gaussian Splatting + AI Foundation Models = ? 🤔. Feature 3DGS🪄, distills feature fields from 2D foundation models, opening the door to a brand new semantic, editable, and promptable explicit 3D scene representation. AI for 2D, now in 3D! 🚀. 🔗
0
0
4
It is an immense honor, and I am profoundly grateful to have my work commented on by Prof. Vincent Sitzmann @vincesitzmann 😊. News link:
ee.ucla.edu
Shijie Zhou, a PhD student advised by Prof. Achuta Kadambi at UCLA Henry Samueli School of Engineering, has received the
0
0
3
RT @janusch_patas: DreamScene360.Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting.Projec….
0
21
0
RT @_akhaliq: DreamScene360. Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting. The increasing demand for virtual….
0
27
0
Feature 3DGS was selected as a ✨Highlight✨ paper (2.8% of all submissions) at #CVPR2024 🥳. Check out our latest magic 🤩.Project Page: Paper: Code: Let's pack our raincoat for Seattle! 🚀.
github.com
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields - ShijieZhou-UCLA/feature-3dgs
(1/5).3D Gaussian Splatting + AI Foundation Models = ? 🤔. Feature 3DGS🪄, distills feature fields from 2D foundation models, opening the door to a brand new semantic, editable, and promptable explicit 3D scene representation. AI for 2D, now in 3D! 🚀. 🔗
0
5
26
RT @WayneINR: Just learned #Sora refines prompts to boost user input. Similarly, our latest study, co-led with @Ir1dXD and @ShijieZhoucla….
0
12
0
(5/5).For more technical details, check out our paper at Really fun collaboration with the team at @UCLA @ECE_UCLA @UCLA_VMG and @UTAustin @VITAGroupUT: Haoran Chang, Sicheng Jiang, @WayneINR, Zehao Zhu,@Ir1dXD, @PradyumnaChari, Atlas Wang, @AchutaKadambi.
0
1
6
(4/5).Segment anything in a 3D scene, without invoking the original SAM workflow - now, it's a tangible reality.
1
1
6
(3/5).The nature of explicit scene representation, coupled with feature fields, enables precise geometry and appearance editing in 3D prompted by natural language. No task-specific fine-tuning, only 18 training view images is all you need for this complex real-world scene.
1
1
6