great work on reflect3r from @jingwu23 and co from @3DVconf. the dataset has 16 synthetic blender interior scenes, each with a mirror, rendered from both a real camera and a geometrically derived virtual mirror camera, along with ground-truth point clouds
Excited to share that our synthetic evaluation benchmark is now integrated into @Voxel51.
Huge thanks to Harpreet Sahota and the @Voxel51 team for making this happen!
Check it out 👉: https://t.co/NY4zzckZTt
📣📣 Introducing Reflect3r @3DVconf
✅ Single-view to 3D reconstruction by using mirror reflections as an auxiliary view
✅ A synthetic evaluation dataset containing 16 fully customizable Blender scenes.
This is a joint work with @ziruiwang_, Iro Laina, and @viprad
🌐 Project Page: https://t.co/9X66b0dIrH
📄 Paper: https://t.co/nk5NWyKOUv
👩💻 Code: https://t.co/Jv3JxE2aER
🤗 Huggingface: https://t.co/VEji2srAru
🚀 Introducing the Qwen 3.5 Small Model Series
Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B
✨ More intelligence, less compute.
These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL:
• 0.8B / 2B → tiny, fast, great for edge device
• 4B → a surprisingly strong multimodal base for lightweight agents
• 9B → compact, but already closing the gap with much larger models
And yes — we’re also releasing the Base models as well.
We hope this better supports research, experimentation, and real-world industrial innovation.
Hugging Face: https://t.co/wFMdX5pDjU
ModelScope: https://t.co/9NGXcIdCWI
📣📣 Introducing OS-Marathon⏱️
I am proud to share this interesting project I did during my internship @Microsoft@MSFTResearch. 🥳
This work is about benchmarking computer-use agents' ability on a type of long-horizon, repetitive tasks.
✅ We focus on desktop workflows that are long-horizon and also repetitive, e.g. filling the expense system given a set of various travelling receipts.
✅ We create data, build tasks and environments and categorise them into multiple difficulty levels to enable fine-grained evaluation.
📎Project Page: https://t.co/NORAd1ptuL
📄Paper: https://t.co/UxERGlevQb
Joint work with Daphne Barretto, Yiye Chen, Nicholas Gydé, Yanan Jian, Yuhang He @HenryOxplore, Vibhav Vineet @VibhavVineet
📣📣 Introducing Reflect3r @3DVconf
✅ Single-view to 3D reconstruction by using mirror reflections as an auxiliary view
✅ A synthetic evaluation dataset containing 16 fully customizable Blender scenes.
This is a joint work with @ziruiwang_, Iro Laina, and @viprad
🌐 Project Page: https://t.co/9X66b0dIrH
📄 Paper: https://t.co/nk5NWyKOUv
👩💻 Code: https://t.co/Jv3JxE2aER
🤗 Huggingface: https://t.co/VEji2srAru
Excited to share that our Oxford Day-and-Night dataset has been accepted to the NeurIPS 2025 Dataset track! See you in San Diego!
📦 Dataset: https://t.co/FGOKTaKv5W
🌐 Project Page: https://t.co/VDbGYgKq5z
🥳 We are going to present our poster GaussCtrl at #ECCV2024 in Milan! @eccvconf
Feel free to come and say hi to my poster if you're interested!! 😼
🗓️ Thu 3 Oct 4:30 p.m. CEST — 6:30 p.m. CEST, Poster #261
See you there!!😉
🌐 https://t.co/GKGVV4CFYa
🥳 We are going to present our poster GaussCtrl at #ECCV2024 in Milan! @eccvconf
Feel free to come and say hi to my poster if you're interested!! 😼
🗓️ Thu 3 Oct 4:30 p.m. CEST — 6:30 p.m. CEST, Poster #261
See you there!!😉
🌐 https://t.co/GKGVV4CFYa
Oh wow! I just tested Splatt3R with my own data on my computer, which creates 3D Gaussian Splats at 4 FPS on uncalibrated 512x512 2D images!
It's by far the fastest 3D reconstruction method, powered by MASt3R.
Check out the video!
📢📢 📢 Introducing GaussCtrl!!
✅Easy control your Gaussian Splatting model with a text prompt! 🤩
✅Remarkable multi-view consistency quality!
w/ Jia-Wang Bian, @li_xinghui@wanggrun, Ian Reid, Philip Torr, and @viprad
🌐https://t.co/OexUS2NiSP
📰https://t.co/B2jbgL7DV0
📢📢 📢 Introducing GaussCtrl!!
✅Easy control your Gaussian Splatting model with a text prompt! 🤩
✅Remarkable multi-view consistency quality!
w/ Jia-Wang Bian, @li_xinghui@wanggrun, Ian Reid, Philip Torr, and @viprad
🌐https://t.co/OexUS2NiSP
📰https://t.co/B2jbgL7DV0
Diffusion models for imaging and vision
Just made this set of slides for an upcoming talk. Feedback is welcome!
Slides: https://t.co/lmFfMHMXAJ
Tutorial (March version): https://t.co/fWv111nG5M
(Thx for messaging me the typos. Still working on them.)
"The Construction of a Neon City" 🌆
Supercharging a static Midjourney picture with Photoshop's Generative Fill, WORKFLOW
Time spent: 3 hours 10 minutes. Complexity 6/10
Sound On 🔊