Philipp Schröppel

I am a PhD student in the Computer Vision Group at the University of Freiburg, headed by Prof. Thomas Brox.

My broad research interest is 3D reconstruction in terms of 3d geometry, ego‑motion and object motion. A particular focus is robust application on arbitrary real‑world data.

Recently, I worked on 3D generation using diffusion models. Currently, I am most interested in fundamental research on diffusion models, and in using scene priors learnt by diffusion models for 3D reconstruction.

Email  /  CV  /  Scholar  /  Twitter  /  Github

profile photo

Publications

DOoD Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond
Silvio Galesso*, Philipp Schröppel*, Hssan Driss, Thomas Brox (* denotes equal contribution)
ECCV, 2024
Paper / Code / ADE-OoD Benchmark / Bibtex

We introduce ADE-OoD, a novel benchmark for out-of-distribution (OoD) detection for semantic segmentation on general natural images, and DOoD, a diffusion-based method that detects OoD samples by perturbing them and checking the directional error of the estimated score.

NPCD Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation
Philipp Schröppel, Christopher Wewer, Jan Eric Lenssen, Eddy Ilg, Thomas Brox
CVPR, 2024
Paper / Project page / Code / Bibtex

We generate 3D shape and appearance of objects via diffusion on neural point clouds (points with a 3D position and a learned feature). As the point positions represent the coarse shape and the features represent the appearance, shape and appearance can be generated separately.

RMVD A Benchmark and a Baseline for Robust Multi-view Depth Estimation
Philipp Schröppel, Jan Bechtold, Artemij Amiranashvili, Thomas Brox
3DV, 2022
Paper / Code / Bibtex

We introduce a benchmark for robust zero-shot multi-view depth estimation and evaluate many recent models. We present a new model that works more robustly across data from different domains and can serve as a baseline for future evaluations on the benchmark.

SF2SE3 SF2SE3: Clustering Scene Flow into SE (3)-Motions via Proposal and Selection
Leonhard Sommer, Philipp Schröppel, Thomas Brox
GCPR, 2022
Paper / Code / Bibtex

We propose SF2SE3, an approach estimate a moving object segmentation and corresponding SE(3) motions from optical flow and depth. It works by iteratively sampling motion proposals and selecting the best ones with respect to a maximum coverage formulation.

SF2SE3 Semi-Supervised Disparity Estimation with Deep Feature Reconstruction
Julia Guerrero-Viu, Sergio Izquierdo, Philipp Schröppel, Thomas Brox
CVPR Women in Computer Vision Workshop, 2021
Paper

We train a network for disparity estimation in a semi-supervised fashion on labeled synthetic data and unlabeled real data. For supervision on the unlabeled data, we explore a deep feature reconstruction loss, instead of the commonly used photometric loss.


The template for this website comes from Jon Barron. Thanks!