Tobias Fischer Profile
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
Don't wanna be here? Send us removal request.
@TobiasFischer11
Tobias Fischer
21 days
RT @ShengyHuang: Great opportunity to build cool stuff with brilliant minds.
0
1
0
@TobiasFischer11
Tobias Fischer
28 days
RT @JonathonLuiten: Monocular Dynamic Reconstruction is HARD!. Single video input –> A LOT of 3D ambiguity –> Significant visual artifa….
0
7
0
@TobiasFischer11
Tobias Fischer
28 days
🌊🏄.
@JonathonLuiten
Jonathon Luiten
28 days
Accepted to ICCV with perfect review scores!!!. See you all in Hawaii!!!!.
1
0
8
@TobiasFischer11
Tobias Fischer
2 months
RT @LinfeiPan: 📢 Introducing GenSfM – a generic Structure-from-Motion pipeline built on COLMAP, with smooth, invertible, and universal cali….
0
36
0
@TobiasFischer11
Tobias Fischer
2 months
RT @lealtaixe: The time for new architectures is over? Not quite! SeNaTra, a native segmentation backbone, is waiting, let's see how it wor….
Tweet card summary image
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
@TobiasFischer11
Tobias Fischer
3 months
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) 👏.
@zador_pataki
Zador Pataki
3 months
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
@TobiasFischer11
Tobias Fischer
4 months
RT @efedele16: ✨We introduce SuperDec, a new method which allows to create compact 3D scene representations via decomposition into superqua….
0
37
0
@TobiasFischer11
Tobias Fischer
4 months
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
@TobiasFischer11
Tobias Fischer
4 months
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
@TobiasFischer11
Tobias Fischer
4 months
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
@TobiasFischer11
Tobias Fischer
6 months
RT @Shalev_lif: As we learn to use compute more efficiently, we will use more compute.
0
2
0
@TobiasFischer11
Tobias Fischer
7 months
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
@TobiasFischer11
Tobias Fischer
7 months
That‘s a wrap! Thanks to the organizers of @NeurIPSConf for putting together an amazing conference. See you soon Vancouver (what a beautiful venue!) 🛫
Tweet media one
0
0
5
@TobiasFischer11
Tobias Fischer
7 months
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! :).
@TobiasFischer11
Tobias Fischer
1 year
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
@TobiasFischer11
Tobias Fischer
8 months
RT @AntonObukhov1: Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Dept….
0
109
0
@TobiasFischer11
Tobias Fischer
8 months
RT @zhenjun_zhao: SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving. Georg Hess, Carl Lindstr….
0
5
0
@TobiasFischer11
Tobias Fischer
10 months
Happy to share that our paper was accepted as spotlight @NeurIPSConf 2024! See you in Vancouver 🇨🇦.
@TobiasFischer11
Tobias Fischer
1 year
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
@TobiasFischer11
Tobias Fischer
10 months
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
@TobiasFischer11
Tobias Fischer
10 months
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