Introducing LaRI (ruili3.github.io/lari), a📸single-view,🚀single-feed-forward method to model🙈unseen 3D geometry using layered point maps. It ✅seamlessly extends depth estimation ✅unifies object- & scene-level reasoning ✅builds training & eval datasets Details👇

Zang et al., "World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible" A Diffusion Transformer that estimates multiple layers of depth to further estimate occluded parts as well.

Natural images often already implicitly contain depth information — hidden in bokeh effects. Can we leverage the rich depth cue widely exist in natural images for depth estimation? We explore this in our recent project BokehDepth (ICML 2026). - Stage 1: A generative model produces calibrated bokeh stacks from the input image. - Stage 2: The bokeh stacks are integrated into a depth prediction model to estimate depth. We believe it highlights bokeh effects as an important and effective complementary cue for monocular depth estimation. 🌐 Project page: fogradio.github.io/BokehDept… 📄 arXiv: arxiv.org/abs/2512.12425 👨‍💻 Code: github.com/fogradio/BokehDep…

Come check out V-DPM @CVPR [Poster 25] 11:45 - 13:45 4D video reconstruction in the wild: code and models available 🤖 @EldarIsTyping @Oxford_VGG

Transformers have succeeded in modeling phenomena traditionally associated with computer graphics, such as 3D visual effects (e.g., RayZer) and rendering processes (e.g., RenderFormer). A natural question is whether they can also tackle the challenging task of cloth simulation. We introduce 👕𝗖𝗹𝗼𝘁𝗵𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿, a Transformer-based method that reformulates cloth simulation as autoregressive next-state prediction in a learned latent space. It handles diverse scenarios under a single model, with 4-9x lower error than prior SOTAs: • Body-driven garments • Robotic manipulation • General cloth–object collisions We believe it highlights the potential of Transformer-based autoregressive models as a powerful alternative to conventional simulation approaches. This work is mainly led by my student Yu Zhang @yucrazing 🌐 Project page: yucrazing.github.io/clothtra… 📄 arXiv: arxiv.org/abs/2605.27852

The current paper submission and review process seems unlikely to survive LLMs. One alternative would be to build a new process around talks: "submission" is making and giving a 30 minute live talk, and "review" is three experts watching, evaluating, and asking questions.

🎺Meet VIST3A — Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator. ➡️ Paper: arxiv.org/abs/2510.13454 ➡️ Website: gohyojun15.github.io/VIST3A/ Collaboration between ETH & Google with Hyojun Go, @DNarnhofer, Goutam Bhat, @fedassa, and Konrad Schindler.

🚀Excited to share our recent work on test-time scaling for feed-forward Gaussian splatting: we learn a recurrent model ReSplat that is able to iteratively improve the reconstruction quality in a feed-forward manner! haofeixu.github.io/resplat/

Interesting ICLR submissions 🤩 Depth Anything 3 - My TLDR: Init multi view transformer of VGGT with later layer DINO weights and use teacher model trained on synthetic data only for pseudo labelling real world datasets openreview.net/forum?id=yiru… Trace Anything - My TLDR: VGGT like model predicting N view geometry and motion as a trajectory field represented using splines and control points openreview.net/forum?id=BqaC… The field is evolving very fast!

Thanks, AK, for sharing our work!