activity
20202024
most citedTransformerFusion: Monocular RGB Scene Reconstruction using Transformers

31 citations · 34 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV2024

3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt

Lukas Höllein, Aljaž Božič, Michael Zollhöfer +1

We present 3DGS-LM, a new method that accelerates the reconstruction of 3D Gaussian Splatting (3DGS) by replacing its ADAM optimizer with a tailored Levenberg-Marquardt (LM). Exist…

cs.CV2024★ 3 cited

ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models

Lukas Höllein, Aljaž Božič, Norman Müller +5

3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-i…

cs.CV2023

Neural Lens Modeling

Wenqi Xian, Aljaž Božič, Noah Snavely +1

Recent methods for 3D reconstruction and rendering increasingly benefit from end-to-end optimization of the entire image formation process. However, this approach is currently limi…

cs.CV2021★ 31 cited

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers

Aljaž Božič, Pablo Palafox, Justus Thies +2

We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. From an input monocular RGB video, the video frames are processed by a transformer network tha…

cs.CV2021

NPMs: Neural Parametric Models for 3D Deformable Shapes

Pablo Palafox, Aljaž Božič, Justus Thies +2

Parametric 3D models have enabled a wide variety of tasks in computer graphics and vision, such as modeling human bodies, faces, and hands. However, the construction of these param…

cs.CV2020

Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction

Aljaž Božič, Pablo Palafox, Michael Zollhöfer +3

We introduce Neural Deformation Graphs for globally-consistent deformation tracking and 3D reconstruction of non-rigid objects. Specifically, we implicitly model a deformation grap…