Tobias Fischer
@tobiasfshr.bsky.social
Research Scientist Intern @ NVIDIA
PhD Student @ CVG, ETH Zurich
Prev. @ Meta Reality Labs, UC Berkeley, RWTH
Dynamic 3D Vision, NeRFs, 3DGS
tobiasfshr.github.io
PhD Student @ CVG, ETH Zurich
Prev. @ Meta Reality Labs, UC Berkeley, RWTH
Dynamic 3D Vision, NeRFs, 3DGS
tobiasfshr.github.io
Project Page: tobiasfshr.github.io/pub/flowr/
FlowR: Flowing from Sparse to Dense 3D Reconstructions | Tobias Fischer
We present FlowR, a novel pipeline that bridges the gap between sparse and dense 3D reconstruction. Contrary to prior works, we learn a direct mapping between incorrect renderings and their correspond...
tobiasfshr.github.io
April 3, 2025 at 2:48 PM
Project Page: tobiasfshr.github.io/pub/flowr/
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).
April 3, 2025 at 9:34 AM
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).
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.
(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.
April 3, 2025 at 9:33 AM
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.
(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.