📽️ Check out Visual Odometry Transformer! VoT is an end-to-end model for getting accurate metric camera poses from monocular videos.

vladimiryugay.github.io/vot/

#TTT3R: 3D Reconstruction as Test-Time Training
TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required!
🔗Page: rover-xingyu.github.io/TTT3R
We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D!

distortion_averaging/simple_calibration_unique_cameras.ipynb at main · DaniilSinitsyn/distortion_averaging PRaDA: Projective Radial Distortion Averaging. Contribute to DaniilSinitsyn/distortion_averaging development by creating an account on GitHub.

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.

Check out the jupyter notebook for a typical example with python bindings github.com/DaniilSinits...

🦖 We present “Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion”. #ICCV2025
🌍: visinf.github.io/scenedino/
📃: arxiv.org/abs/2507.06230
🤗: huggingface.co/spaces/jev-a...
@jev-aleks.bsky.social @fwimbauer.bsky.social @olvrhhn.bsky.social @stefanroth.bsky.social @dcremers.bsky.social

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

arxiv.org/abs/2504.16499
github.com/DaniilSinits...

Can we match vision and language representations without any supervision or paired data?

Surprisingly, yes! 

Our #CVPR2025 paper with @neekans.bsky.social and @dcremers.bsky.social shows that the pairwise distances in both modalities are often enough to find correspondences.

⬇️ 1/4

Can you train a model for pose estimation directly on casual videos without supervision?

Turns out you can!

In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors!

⬇️

Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. Howeve...

Our paper, ”Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation”, has been accepted to #CVPR 2025.

📄 Paper: arxiv.org/abs/2503.21780
🧪 Code: github.com/rezaqorbani/...

Very glad to announce that our "Finsler Multi-Dimensional Scaling" paper, accepted at #CVPR2025, is now on Arxiv! arxiv.org/abs/2503.18010

AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration

Javier Tirado-Garín, @jcivera.bsky.social

tl;dr: image->ViT+DPT->Field of View (FoV) fields->bijective rays and corresponding image coordinates->closed-form model-agnostic intrinsics

arxiv.org/abs/2503.12701

We are thrilled to have 12 papers accepted to #CVPR2025. Thanks to all our students and collaborators for this great achievement!
For more details check out cvg.cit.tum.de

MUSt3R: Multi-view Network for Stereo 3D Reconstruction

Yohann Cabon, Lucas Stoffl, Leonid Antsfeld, Gabriela Csurka, Boris Chidlovskii, Jerome Revaud, @vincentleroy.bsky.social

tl;dr: make DUSt3R symmetric and iterative+multi-layer memory mechanism->multi-view DUSt3R

arxiv.org/abs/2503.01661

🥳 Thrilled to announce that our work, "4Deform: Neural Surface Deformation for Robust Shape Interpolation," has been accepted to #CVPR2025 🙌
💻 Check our project page: 4deform.github.io
👏 Great thanks to my amazing co-authors. @ricmarin.bsky.social @dongliangcao.bsky.social @dcremers.bsky.social

in practice the angle between the observation ray and principal axis will always be limited by the camera fov, so not sure how much difference the fix would do tbh

but yeah, eg if translation noise is the main source of error I could see midpoint being optimal!

consider me nerd-sniped 😅 one benefit I can see for the reprojection error is that it gives a better tradeoff when cameras are at different distances.

Here's a 3-view example:
blue=GT point
red=optimal projection error
green=optimal point-to-ray distance

all views have the same observation noise

🥳Thrilled to share our work, "Implicit Neural Surface Deformation with Explicit Velocity Fields", accepted at #ICLR2025 👏
code is available at: github.com/Sangluisme/I...
😊Huge thanks to my amazing co-authors. @dongliangcao.bsky.social @dcremers.bsky.social
👏Special thanks to @ricmarin.bsky.social

Indeed - everyone had a blast - thank you all for the great talks, discussions and Ski/snowboarding!

DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting, presented at #ECCV2024

Paper: arxiv.org/abs/2407.17058
Code/project: github.com/linusnie/dif...

Reposting some of my prior works here on this site :) "Semidefinite Relaxations for Robust Multiview Triangulation" at #CVPR2023!

paper: arxiv.org/abs/2301.11431
code: github.com/Linusnie/rob...