Philipp Schröppel

I am a PhD candidate in the Computer Vision Group at the University of Freiburg, headed by Thomas Brox. Recently, I did a research visit at the Visual Intelligence & Perception Lab within the Max Planck Institute for Informatics, headed by Jan Eric Lenssen.

In recent years, I have worked on 3D computer vision, diffusion-based generative models, and object-centric learning.

Currently I am most interested in generative 3D reconstruction, world models, robotics, LLMs, and algorithms that learn compact, composable, abstract representations.

Also, I develop and maintain the Robust Multi-view Depth (robustmvd) benchmark and framework. It allows the use and evaluation of depth estimation models with a common interface.

Email  /  Scholar  /  Twitter  /  Bluesky  /  Github

Publications

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.

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.

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.

We propose SF2SE3, an approach to 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.

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.

Academic Activities

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