Very excited to announce our paper: "DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting" at #ECCV2024!. Paper: Code/project:

RT @mateodemayo: Our paper "The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking" has been accepted at #IROS2025!. Because SLAM/….

Blazing-fast image creation – using just your voice. Try Grok Imagine.

Also check out the jupyter notebook for a typical example with python bindings.

The key is working in projective space, estimating only fundamental matrices and distortion parameters. These can then be used to initialize full SfM, leading to an overall more robust pipeline. Paper:

The code for our #CVPR2025 paper, PRaDA: Projective Radial Distortion Averaging, is now out!. Turns out distortion calibration from multiview 2D correspondences can be fully decoupled from 3D reconstruction, greatly simplifying the problem.

RT @ChristophR1996: 🦖 We present “Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion”. #ICCV2025.🌍: .

RT @tumcvg: Join us for a full-day 3D Shape Analysis tutorial at @CVPR in Nashville, on Thursday, June 12, from 9:15 AM to 5:00 PM in Room….

RT @dominik_schnaus: Can we match vision and language representations without any supervision or paired data?. Surprisingly, yes! . Our #CV….

RT @felixwimbauer: Can you train a model for pose estimation directly on casual videos without supervision?. Turns out you can!. In our #CV….

RT @felixwimbauer: Check out our recent #CVPR2025 paper AnyCam, a method for pose estimation in casual videos! . 1️⃣ Can be directly train….

RT @ducha_aiki: Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction. Weirong Chen, Ganlin Zhang, @felixwimbauer , Rui Wang, @….

RT @tumcvg: We are thrilled that our group has twelve papers accepted at #CVPR2025! 🚀.Congratulations to all of our students for this great….

RT @Lu_Sang__: 🥳 Thrilled to announce that our work, "4Deform: Neural Surface Deformation for Robust Shape Interpolation," has been accept….

RT @rmurai0610: Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation. Easy to use like DUSt3R/MA….

We are presenting DiffCD tomorrow morning at #ECCV2024!. Come by poster 214 to discuss how to fit neural SDFs to point clouds, from a geometric perspective.

RT @SimWeberTUM: Looking forward to present "PoVar" at #ECCV2024 tomorrow at 4:30pm, Poster 097 !.Check out our paper 📝 : .

RT @SattlerTorsten: This looks like it will enable a lot of cool research:

RT @tumcvg: Some good news for the summer:. We are very proud that the students of our lab, together with great collaborators, are going to….

See the paper for more details. We also provide the code for reproducing all figures from the paper in the github repo(!). Co-authors: @Lu_Sang__, @abhi_saroha19, @neekans and Daniel Cremers.

As a theoretical contribution, we also analyze the loss term from SIREN, which is another way to deal with spurious surfaces. Using the "co-area" formula, we show that the SIREN approach leads to regularizing surface area; reducing surface detail. DiffCD avoids this tradeoff!

Our method adds the "missing" Chamfer term: the average distance from the surface to the point cloud! This ensures that spurious surfaces, which are in the "blind spot" of the one-sided Chamfer Distance, are taken into account.