Roni Itkin (@ItkRoni) profile picture

Researcher at The Hebrew University of Jerusalem | 3D Vision and Computer Graphics

Joined March 2025
Photo by Roni Itkin (@ItkRoni)Photo by Roni Itkin (@ItkRoni)Photo by Roni Itkin (@ItkRoni)Photo by Roni Itkin (@ItkRoni)Photo by Roni Itkin (@ItkRoni)
Thrilled to share that GlobalSplat is accepted to ECCV 2026! 🎉 Instead of tying Gaussians to input pixels, GlobalSplat aggregates multi-view input into a fixed-size bank of global scene tokens - align first, decode later - for compact, view-count-agnostic feed-forward novel-view synthesis. As few as 2K–32K Gaussians, ~4 MB, <78 ms single pass. Work with @YehonatanKe @IssacharNoam @RoverXingyu @AnpeiC @BenaimSagie. 🎥 Project page: r-itk.github.io/globalsplat 💻 Code coming soon - star the repo and stay tuned! #ECCV2026 #GaussianSplatting #3DVision
We introduce 🌍GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens.🌍 Most feed-forward 3DGS methods still start from pixel, voxel, or dense view-aligned primitives. We take a different route: align first, decode later. 🧵👇
2
8
30
4,145
Colored Noise Diffusion Sampling (CNS) has been accepted to #NeurIPS2026 as an Oral! 🎉 🌐Project Page: hadardavidson.github.io/CNS 📄Paper: arxiv.org/abs/2605.30332 💻Code: github.com/hadardavidson/col… With @IssacharNoam and @BenaimSagie.
Excited to share Colored Noise Sampling (CNS)!🎉 Instead of injecting white noise, our SDE sampler exploits the inherent spectral bias of diffusion models. We dynamically color the injected noise to focus on frequencies where details are missing, substantially improving FID.🧵1/9
7
26
2
230
20,201
Roni Itkin retweeted
Only in America. Tired of winning?
Giving birth in Europe vs in America 😂
212
103
15
1,392
506,352
Roni Itkin retweeted
Excited to announce that "MV-Forcing" has been accepted to #ECCV2026! 🎉 Current methods generate long single-view videos or short multi-view videos, but not both. To bridge this gap, we present MV-Forcing, the first framework for long multi-view video generation. [1/6]
1
10
2
35
6,367
Roni Itkin retweeted
1/6 Diffusion models are scaling up, but deploying a massive, monolithic network uniformly across the entire generative timeline is inherently inefficient. Introducing Complexity-Balanced Splitting (CBS): a principled framework that allocates capacity exactly where needed!👇🧵
1
12
33
605
Roni Itkin retweeted
🚨 Excited to share our new paper: "PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions"! 🎉 We tackle generating photorealistic 4D interactions by deeply coupling generative human motion diffusion with physical simulation! 🧠💥🧵👇(1/4)
3
6
1
19
472
Excited to share Colored Noise Sampling (CNS)!🎉 Instead of injecting white noise, our SDE sampler exploits the inherent spectral bias of diffusion models. We dynamically color the injected noise to focus on frequencies where details are missing, substantially improving FID.🧵1/9
5
37
2
320
36,313
Roni Itkin retweeted
We suggest going back to relative pose modeling, enabling efficient and robust 3D reconstruction with low memory overhead — in both streaming and offline settings. Project: kevinxu02.github.io/r3-site/ Paper: arxiv.org/abs/2605.26519
14
99
8,788
Roni Itkin retweeted
Our paper: "LaMI: Augmenting Large Language Models via Late Multi-Image Fusion" has been selected for an Oral Presentation at #ACL2026! LaMI boosts LLM visual commonsense by generating complementary images from a text prompt and late-fusing their evidence into the prediction 🧵
6
17
1
65
4,926
Happy to share that our work "RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes" was accepted to #CVPR2026 (findings). Check out the project page: michaelbaltaxe.github.io/rad…
2
15
1
74
5,415
Very excited to share the first paper from my postdoc, led by the talented @JieZhang_ETH . This was an extremely fun project with a great group of people 🥸
I was hoping to do a live demo of what @JieZhang_ETH @poonpura and @AvitalShafran have been cooking, but I didn't get a blue checkmark for my birthday so I can't call Grok from this account. Screenshots from our lab's alt account will have to do. like this one 👇
3
6
1
27
1,242
Roni Itkin retweeted
✨Happy to share that our paper DyPE has been accepted to #ICML2026!
We present DyPE, a framework for ultra high resolution image generation. DyPE adjusts positional embeddings to evolve dynamically with the spectral progression of diffusion. This lets pre-trained DiTs create images with 16M+ pixels without retraining or extra inference cost. 🧵👇
4
1
26
4,722
Roni Itkin retweeted
Replying to @ItkRoni
🌍GlobalSplat🌍is sparse by design. It places Gaussian centers only where the scene is occupied, and uses fewer, larger Gaussians in simpler regions. Better feed-forward 3DGS starts with better primitive allocation.
1
4
277
Roni Itkin retweeted
GlobalSplat: Stop unprojecting, start decoding. 🛠️ We fuse all input views into a fixed set of Global Scene Tokens to build high-fidelity 3D assets without the pixel-wise redundancy. ✅ Higher quality ✅ Better spatial allocation 🔗 r-itk.github.io/globalsplat/ #3DGS
3
39
2
281
19,547
Roni Itkin retweeted
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens @ItkRoni, @IssacharNoam, @YehonatanKe, @RoverXingyu, @AnpeiC, @BenaimSagie tl;dr: all input views->a fixed number of latent scene tokens->decoder->explicit 3D Gaussians arxiv.org/abs/2604.15284
3
5
40
2,693
We introduce 🌍GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens.🌍 Most feed-forward 3DGS methods still start from pixel, voxel, or dense view-aligned primitives. We take a different route: align first, decode later. 🧵👇
1
18
3
49
7,062
Strong efficiency-quality operating point: 24 Views on A100: 1.79 GB peak GPU memory 77.88 ms inference 3.8 MB on disk With as few as 2–32K Gaussians, 🌍GlobalSplat🌍 has better PSNR on RE10K then feed-forward 3DGS methods that use hundreds of thousands to millions of Gaussians.
1
3
366