Searcharxiv⌕ Search

arXiv subjects

Jona Ruthardt

Publications and source records attributed to Jona Ruthardt.

5 recordsLinked to original sources

Open Vision Banana: A Fully Open Recipe for Generative Visual Perception

Recent work suggests that pretrained image generators encode real-world understanding beyond image synthesis. Vision Banana exploits this by framing vision tasks as conditional image editing. However, its data, weights, code, and implementation details are not public. We present Open Vision Banana (OVB), a fully open and reproducible recipe for converting pretrained generators into unified multi-task perception systems. Our analyses identify the design choices that matter most for generalization, including color encoding, prompt design, parameter adaptation, and task balancing. These choices interact, so individually helpful choices can hurt when combined with others. Starting from 4B and 9B parameter open-weight base models and using 2.1M-3.8M training pairs from public datasets, OVB surpasses Vision Banana's reported Cityscapes zero-shot performance (73.9 vs. 69.9 mIoU) and rivals state-of-the-art affine-invariant depth estimators. Its non-zero-shot variants come within five points of Vision Banana on referring and reasoning segmentation but remain further behind on instance segmentation. All models largely retain the base model's image-editing abilities. With legend ensembling, we introduce a test-time scaling method for generator-based perception. It segments an image under several class-color legends and fuses the results by majority vote, correcting unstable color-class bindings and improving mIoU by up to 8.7 points on Cityscapes and 15.0 points on COCO-Object without retraining. We release the dataset construction and processing pipeline, the training and evaluation code, as well as the final, intermediate, and ablation checkpoints. Project website: https://openvisionbanana.github.io

cs.CV↗

Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents

Multimodal Large Language Models (MLLMs) are emerging as core reasoning modules for embodied agents, yet it remains unclear how well general-purpose models can solve long-horizon embodied tasks from a single high-level instruction. We introduce MissionBench, a benchmark for mission-level evaluation of MLLMs in aerial 3D environments. It comprises 120 missions across five simulated 3D environments and four task families. Agents must autonomously plan, navigate, and report outcomes using only egocentric observations and its action history, without aerial-specific fine-tuning. Across 22 open- and closed-source MLLMs, the strongest model succeeds on fewer than 35% of missions compared to 84.4% human performance, highlighting the difficulty of multi-step embodied tasks. Despite large variations between model families, we observe gains from scaling, indicating that larger general-purpose models possess stronger zero-shot embodied capabilities. Our analysis shows that mission-level competence requires coordinating multiple capabilities beyond spatial perception, including multi-step planning and adaptive reasoning. This motivates closed-loop evaluation and highlights both the promise and risk of scaling-driven improvements for embodied AI.

cs.AI↗

Steerable Visual Representations

Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to focus on the most salient visual cues in the image, with no way to direct them toward less prominent concepts of interest. In contrast, Multimodal LLMs can be guided with textual prompts, but the resulting representations tend to be language-centric and lose their effectiveness for generic visual tasks. To address this, we introduce Steerable Visual Representations, a new class of visual representations, whose global and local features can be steered with natural language. While most vision-language models (e.g., CLIP) fuse text with visual features after encoding (late fusion), we inject text directly into the layers of the visual encoder (early fusion) via lightweight cross-attention. We introduce benchmarks for measuring representational steerability, and demonstrate that our steerable visual features can focus on any desired objects in an image while preserving the underlying representation quality. Our method also matches or outperforms dedicated approaches on anomaly detection and personalized object discrimination, exhibiting zero-shot generalization to out-of-distribution tasks.

cs.CV↗

Better Language Models Exhibit Higher Visual Alignment

How well do text-only large language models (LLMs) align with the visual world? We present a systematic evaluation of this question by incorporating frozen representations of various language models into a discriminative vision-language framework and measuring zero-shot generalization to novel concepts. We find that decoder-based models exhibit stronger visual alignment than encoders, even when controlling for model and dataset size. Moreover, language modeling performance correlates with visual generalization, suggesting that advances in unimodal LLMs can simultaneously improve vision models. Leveraging these insights, we propose ShareLock, a lightweight method for fusing frozen vision and language backbones. ShareLock achieves robust performance across tasks while drastically reducing the need for paired data and compute. With just 563k image-caption pairs and under one GPU-hour of training, it reaches 51% accuracy on ImageNet. In cross-lingual settings, ShareLock dramatically outperforms CLIP, achieving 38.7% top-1 accuracy on Chinese image classification versus CLIP's 1.4%. Code is available.

cs.CL↗

A System-driven Automatic Ground Truth Generation Method for DL Inner-City Driving Corridor Detectors

Data-driven perception approaches are well-established in automated driving systems. In many fields even super-human performance is reached. Unlike prediction and planning approaches, mainly supervised learning algorithms are used for the perception domain. Therefore, a major remaining challenge is the efficient generation of ground truth data. As perception modules are positioned close to the sensor, they typically run on raw sensor data of high bandwidth. Due to that, the generation of ground truth labels typically causes a significant manual effort, which leads to high costs for the labelling itself and the necessary quality control. In this contribution, we propose an automatic labeling approach for semantic segmentation of the drivable ego corridor that reduces the manual effort by a factor of 150 and more. The proposed holistic approach could be used in an automated data loop, allowing a continuous improvement of the depending perception modules.

cs.CV↗