🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Good post from Balaji on the "verification gap". You could see it as there being two modes in creation. Borrowing GAN terminology: 1) generation and 2) discrimination. e.g. painting - you make a brush stroke (1) and then you look for a while to see if you improved the

🚨 Call for Participation — TRICKY @ ICCV 2025 🌺 Join our challenges on monocular depth & category-level pose for transparent/specular objects! 🧊💎 📅 Challenges: June 📄 Paper due: July 4 🔗 sites.google.com/view/iccv25tri… #ICCV2025 #3DV #AI #CV #TRICKYchallenge

🔥 Very cool to bring paintings to life with Kling 2.1 while visiting the National Gallery in London 🇬🇧 Made with Photo Chat AI

Don’t miss the (4th) Monocular Depth Estimation Workshop at #CVPR2025! Keynotes by Peter Wonka, Yiyi Liao, Konrad Schindler, discussion of the challenge results, and more! Thu 12 Jun, noon PDT, Location: 109 cvpr.thecvf.com/virtual/2025/w…

Monodepth workshop -- now at #CVPR2025 loc. 109! Keynotes by Konrad Schindler Peter Wonka Yiyi Liao, discussion of the challenge results, and more!

Excited to share our CVPR 2025 paper on cross-modal space-time correspondence! We present a method to match pixels across different modalities (RGB-Depth, RGB-Thermal, Photo-Sketch, and cross-style images) — trained entirely using unpaired data and self-supervision. Our

My C++ 3DGS implementation has transitioned to the gsplat backend and is now licensed under Apache 2.0. - Supports MCMC densification by default. - Includes a fused bilateral grid implementation. - A basic viewer, contributed by the community, is available with more features in

It was just one poorly covered mode of distribution.. add more such data, retrain, we are so back

Hunyuan3D-2.1 passed my in-the-wild test 🤯 insanely good model!

Anyone up for replacing Hunyuan3D's 2.1 mesh pipeline with Sparc3D, while keeping their texturing pipeline? The best of two worlds is just one model merge away!

Congrats 🥳🥳 Here are new members of “#CrafterFamily” at #ICCV2025 🍺🍺 TrajectoryCrafter for reshooting your videos with desired camera trajectories; GeometryCrafter for dynamic point clouds monocular reconstruction; NormalCrafter for video surface normal estimation.

New in CGAL: Robust and fast self-intersection removal in triangle meshes! Combining Boolean operations and snap rounding, we remove all self-intersections consistently, for example over all of Thingi10k. Work to be presented at SGP this week. More: cgal.org/2025/06/13/aut…

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering Contributions: • We reformulate video stabilization as a novel 3D grounded scheme of local reconstruction and rendering. This approach is naturally robust to diverse camera

WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields Sadra Safadoust, Fabio Tosi, Fatma Güney, Matteo Poggi tl;dr: rendered depth->reprojection->uncertainty->next best view->later GS arxiv.org/abs/2506.22433

🤯 While the core question is interesting, how come your research group has such an access?

What if we could solve object-centric 3D part assembly / pose estimation without the headache of correspondence matching ? 🤔

cocogold - Marigold for segmentation!

⚡️Today we’re releasing SpatialTrackerV2, the first feedforward model for dynamic 3D reconstruction and point tracking in the world space. Project page: spatialtracker.github.io 🤗 demo: huggingface.co/spaces/Yuxihen…

NeurIPS is pleased to officially endorse EurIPS, an independently-organized meeting taking place in Copenhagen this year, which will offer researchers an opportunity to additionally present their accepted NeurIPS work in Europe, concurrently with NeurIPS. Read more in our blog

Muon is the real deal