Research Scientist @ NVIDIA CV|ML|3D
Zurich, Switzerland
Joined March 2020
- Tweets48
- Following115
- Followers219
- Likes293
Proud to be part of the team and excited to share what we’ve been working on 🚀
KeBingxin retweeted
Yesterday @KBingxin defended his PhD on depth estimation with foundation models.
As a tradition, labmates prepared a themed hat.
It was fun working with you on many impactful projects, Bingxin, all the best in your next spectral adventures!
KeBingxin retweeted
Ke et al., "CAPA: Depth Completion as Parameter-Efficient Test-Time Adaptation"
Fine-tune your foundational model at test time with sparse measurements. Makes a lot of sense if you have, e.g. Lidar measurements with you.
KeBingxin retweeted
🚀 Exciting news! We’re introducing VGG-T³: a scalable model for offline feed-forward 3D reconstruction that finally tackles the "quadratic bottleneck."
Ever wanted to have VGGT reconstruct a 1,000-image scene in seconds instead of 10 minutes and use it for visual localization?
KeBingxin retweeted
Introducing StereoSpace -- our new end-to-end method for turning photos into stereo images without explicit geometry or depth maps. This makes it especially robust with thin structures and transparencies. Try the demo below
KeBingxin retweeted
Running out of multi-view data for 3D reconstruction and generation? 🤠
We show how a camera-conditioned video model can be turned into a generative 3D (and dynamic!) Gaussian Splatting model—trained entirely through self-distillation, no real-world data needed.
🚀 Code & models are out for commercial use: research.nvidia.com/labs/tor…
Kudos to @sherwinbahmani for this amazing work! 🎉
📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model!
We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data.
Check out our results in the video (wait for dynamic scenes in the second half!) :
Project Page: research.nvidia.com/labs/tor…
Code and Models: github.com/nv-tlabs/lyra
Paper: arxiv.org/abs/2509.19296
KeBingxin retweeted
[1/N] 🎥 We've made available a powerful spatial AI tool named ViPE: Video Pose Engine, to recover camera motion, intrinsics, and dense metric depth from casual videos!
Running at 3–5 FPS, ViPE handles cinematic shots, dashcams, and even 360° panoramas.
🔗 research.nvidia.com/labs/tor…
KeBingxin retweeted
Team: Bingxin Ke (@KBingxin), Kevin Qu, Tianfu Wang (@TianfuWang2), Nando Metzger (@NandoMetzger), Shengyu Huang (@ShengyHuang), Bo Li, Anton Obukhov (@AntonObukhov1), Konrad Schindler.
We thank @huggingface for their sustained support.
Original announcement of Marigold Depth (CVPR 2024)
nitter.gq/AntonObukhov1/status/1…
Introducing Marigold 🌼 - a universal monocular depth estimator, delivering incredibly sharp predictions in the wild! Based on Stable Diffusion, it is trained with synthetic depth data only and excels in zero-shot adaptation to real-world imagery. Check it out:
🌐 Website: marigoldmonodepth.github.io/
🤗 Hugging Face Space: huggingface.co/spaces/toshas…
📄 Paper: arxiv.org/abs/2312.02145
👾 Code: github.com/prs-eth/marigold
The team: Bingxin Ke (@KBingxin), yours truly (@AntonObukhov1), Shengyu Huang (@ShengyHuang), Nando Metzger (@NandoMetzger), Rodrigo Caye Daudt (@rcdaudt), and Konrad Schindler.
#ComputerVision #PRS #ETHZurich
KeBingxin retweeted
Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you! Details 🧵
KeBingxin retweeted
Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵
KeBingxin retweeted
BetterDepth is a NeurIPS accept! Congrats to the team and thanks to everyone involved! nitter.gq/AntonObukhov1/status/1…
Unveiling BetterDepth — a plug-and-play diffusion-based refiner for zero-shot monocular depth estimation, compatible with many established depth prediction models.
📕 Paper: huggingface.co/papers/2407.1…
🧩 Other: TBA
Fantastic collaboration between ETH Zurich and Disney Research|Studios, by Xiang Zhang (xiangz-0.github.io/), @KBingxin, @chrysmun, @NandoMetzger, @AntonObukhov1, @MarkusGross63, Konrad Schindler, and Christopher Schroers.
KeBingxin retweeted
BetterDepth is accepted to NeurIPS🎉🚀
nitter.gq/NandoMetzger/status/18…
Spice up your favorite SOTA monodepth network with a diffusion model! We introduce *BetterDepth*, a plug-and-play refiner for zero-shot monodepth estimation.
Paper: huggingface.co/papers/2407.1…
KeBingxin retweeted
Check out our work on fine-tuning of image-conditional diffusion models for depth and normal estimation.
Widely used diffusion models can be improved with single-step inference and task-specific fine-tuning, allowing us to gain better accuracy while being 200x faster!⚡
🧵(1/6)
KeBingxin retweeted
Unveiling BetterDepth — a plug-and-play diffusion-based refiner for zero-shot monocular depth estimation, compatible with many established depth prediction models.
📕 Paper: huggingface.co/papers/2407.1…
🧩 Other: TBA
Fantastic collaboration between ETH Zurich and Disney Research|Studios, by Xiang Zhang (xiangz-0.github.io/), @KBingxin, @chrysmun, @NandoMetzger, @AntonObukhov1, @MarkusGross63, Konrad Schindler, and Christopher Schroers.
KeBingxin retweeted
Spice up your favorite SOTA monodepth network with a diffusion model! We introduce *BetterDepth*, a plug-and-play refiner for zero-shot monodepth estimation.
Paper: huggingface.co/papers/2407.1…
It’s a great success at #CVPR2024! Kudos to our great Marigold team
@AntonObukhov1, @ShengyHuang, @NandoMetzger, @rcdaudt, & Konrad Schindler!
Special mention for our hero behind the scene @AntonObukhov1 who couldn’t come to Seattle for an obvious reason.