Tobias Fischer
@TobiasFischer11
Followers
703
Following
473
Media
11
Statuses
90
Research Scientist Intern @NVIDIA. PhD student at CVG, @ETH Zurich. Previously @Meta @RealityLabs, @RWTH, @berkeley_ai
Zurich, Switzerland
Joined December 2020
RT @JonathonLuiten: Monocular Dynamic Reconstruction is HARD!. Single video input –> A LOT of 3D ambiguity –> Significant visual artifa….
0
7
0
🌊🏄.
Accepted to ICCV with perfect review scores!!!. See you all in Hawaii!!!!.
1
0
8
RT @LinfeiPan: 📢 Introducing GenSfM – a generic Structure-from-Motion pipeline built on COLMAP, with smooth, invertible, and universal cali….
0
36
0
RT @lealtaixe: The time for new architectures is over? Not quite! SeNaTra, a native segmentation backbone, is waiting, let's see how it wor….
arxiv.org
Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping...
0
40
0
Watch MP-SfM crush VGGT and Mast3r-SfM!. Great work on leveraging monocular priors to tackle some of the most challenging problems in SfM (low-overlap, low-parallax, symmetries) 👏.
Excited to share the first paper of my PhD: MP-SfM! #CVPR2025 . We augment SfM with monocular depth & normals to handle extreme low-overlap scenes. 🚀 Code: 📄 Paper: Exciting collaboration with @pesarlin, J.L. Schönberger & @mapo1
0
5
71
RT @efedele16: ✨We introduce SuperDec, a new method which allows to create compact 3D scene representations via decomposition into superqua….
0
37
0
3/3 While (a) 'FlowR (Initial)' helps to disambiguate geometry, many artifacts remain. FlowR fixes these with a multi-view, flow matching model that maps incorrect renderings to ground truth (b).
1
2
16
2/3 FlowR consists of two parts:.(a) A robust initial reconstruction pipeline based on MASt3R/3DGS, designed for both sparse- and dense-view settings. (b) A data densification procedure using flow matching to generate high-quality extra views that improve reconstruction.
1
1
14
1/3 Introducing FlowR 🌸: Flowing from Sparse to Dense 3D Reconstructions. We learn a direct mapping between incorrect renderings and their corresponding ground-truth images, augmenting scene captures with consistent novel, generated views to improve reconstruction quality.
4
40
213
RT @fchollet: Today OpenAI announced o3, its next-gen reasoning model. We've worked with OpenAI to test it on ARC-AGI, and we believe it re….
0
2K
0
That‘s a wrap! Thanks to the organizers of @NeurIPSConf for putting together an amazing conference. See you soon Vancouver (what a beautiful venue!) 🛫
0
0
5
I’ll present our #NeurIPS2024 Spotlight Poster on Friday, 13 Dec 4:30-7:30pm PST in East Exhibit Hall A-C, booth #1505. Please step by to talk large-scale dynamic 3D Gaussians! :).
Dynamic 3D Gaussian Fields for Urban Areas. We optimize a single dynamic scene representation from a set of heterogeneous input sequences of a common geographic area, rendering at interactive speeds while modeling huge appearance and geometry changes.
0
2
30
RT @AntonObukhov1: Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Dept….
0
109
0
RT @zhenjun_zhao: SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving. Georg Hess, Carl Lindstr….
0
5
0
Happy to share that our paper was accepted as spotlight @NeurIPSConf 2024! See you in Vancouver 🇨🇦.
Dynamic 3D Gaussian Fields for Urban Areas. We optimize a single dynamic scene representation from a set of heterogeneous input sequences of a common geographic area, rendering at interactive speeds while modeling huge appearance and geometry changes.
2
3
77
RT @JonathonLuiten: Hyperscape: The future of VR and the Metaverse. Excited that Zuckerberg @finkd announced what I have been working on at….
0
82
0
RT @Normanisation: 📣📣 PhD-Intern for Generative AI 📣📣. We are looking for an intern working on 3D Generative AI for summer 2025!.Apply here….
0
34
0