iiinova — where your digital self keeps evolving

Yixin Chen

@yixinchen.bsky.social

Research Scientist at BIGAI, 3D Vision, prev @UCLA, @MPI_IS, @Amazon, yixchen.github.io

Yixin Chen @yixinchen.bsky.social · 01/04/2025

🚀How to preserve object consistency in NVS, ensuring correct position, orientation, plausible geometry, and appearance? This is especially critical for image/video generative models and world models. 🎉Check out our #CVPR2025 paper: MOVIS (jason-aplp.github.io/MOVIS) 👇 (1/6)

100

Yixin Chen @yixinchen.bsky.social · 21/03/2025

🚀 How to reconstruct 3D scenes with decomposed objects from sparse inputs? Check out DPRecon (dp-recon.github.io) at #CVPR2025 — it recovers all objects, achieves photorealistic mesh rendering, and supports text-based geometry & appearance editing. More details👇 (1/n)

510

Yixin Chen @yixinchen.bsky.social · 14/03/2025

📢📢📢Excited to announce the 5th Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics at #CVPR2025! Expect our awesome speakers and challenges on multi-modal 3D scene understanding and reasoning. 🎉🎉🎉 Learn more at scene-understanding.com.

021