arXiv subjects

Stefan Roth

Publications and source records attributed to Stefan Roth.

At least 19 recordsLinked to original sources

arXiv2026

LucidLyra: Feed-Forward Generative 3D Scene Reconstruction and Joint Understanding via Multi-Task Distillation

We present LucidLyra, a framework that makes generatively reconstructed 3D scenes directly queryable for semantics and instances in a feed-forward manner from video latents. While generative 3D reconstruction can synthesize virtual environments from a single image, downstream applications in robotics and physical AI require not only visual realism but also access to scene semantics and object identities. Existing 3D understanding approaches, however, require captured multi-view scenes, have limited generalization capabilities, or rely on expensive per-scene processing and optimization. To bridge this gap, our method distills complementary knowledge from a camera-controlled video diffusion model and frozen 2D vision foundation models into a unified model to jointly infer 3D Gaussians encoding geometry, appearance, open-vocabulary semantics, and class-agnostic instance cues. The resulting scenes support novel-view rendering, open-vocabulary segmentation, and object grouping without per-scene optimization, while training requires neither manual 3D annotations nor captured multi-view data. Our method outperforms baselines combining state-of-the-art 3DGS segmentation approaches with generative 3D scene reconstruction on curated synthetic and real-image-conditioned benchmarks, while preserving reconstruction quality. Furthermore, our latent formulation naturally extends to monocular video, reconstructing structured dynamic 3D scenes across time. By turning renderable but unstructured outputs into queryable 3D worlds, LucidLyra enables downstream applications including 3D scene editing, 3D asset mining, and robotic simulation.

cs.CV↗

arXiv2026

Importance-Aware Low-Rank Distillation of Diffusion Transformers

Diffusion Transformers (DiTs) have emerged as a dominant architecture for high-quality text-to-image generation, yet their scale poses challenges for efficient deployment. While truncated singular value decomposition (SVD) is a principled tool for parameter reduction, evidence from large language models (LLMs) suggests that naive low-rank approximation can cause catastrophic failure. In contrast, we find that truncated SVD in DiTs produces smooth degradation even under substantial global compression, with redundancy distributed across projection matrices throughout the whole network rather than concentrated in a few transformer blocks. Building on these insights, we introduce SVDtrunc, a two-step block-level compression scheme, first allocating ranks across blocks and compressing the least important ones via truncated SVD under a global parameter budget, and then fine-tuning all blocks with modular knowledge distillation and a rectified-flow objective. We apply SVDtrunc to FLUX.dev across compression levels ranging from 40-90% of the original parameter count. Across three benchmarks, GenEval, HPSv2, and DPG, we outperform all competing approaches. Notably, and in contrast to prior work, we retain near-full performance at 68% and remain competitive even at 57% of the original parameter budget. Furthermore, we show that SVDtrunc complements step distillation and achieves strong results even without fine-tuning, positioning it as a practical continuation of efficiency improvements beyond diffusion step reduction for large-scale generative models. Project page: https://vislearn.github.io/SVDtrunc/

cs.CV↗

arXiv2026

Doppio: A Dataset for Contactless Weight Estimation of Falling Particles

Measuring the mass of powder, including falling particles, is a common task in industrial applications. While scales are effective for static measurements, many applications require contactless sensing, where existing solutions are often costly, application-specific, and technically complex. In this work, we investigate computer vision as a practical alternative for contactless mass estimation. As an accessible real-world case study, we focus on coffee grinding and introduce \emph{Doppio}, a novel video dataset capturing videos of falling ground coffee, paired with precise, per-frame ground-truth weight measurements. To demonstrate contactless measuring, we evaluate deep learning-based approaches ranging from purely spatial feed-forward networks to recurrent spatio-temporal models. These models are analyzed with respect to their predictive accuracy and computational trade-offs. We demonstrate that deep learning-based computer vision models accurately estimate the cumulative weight of falling particles, establishing a solid foundation for future vision-based contactless measurement solutions.

cs.CV↗

arXiv2026

ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views

We introduce ReconSplat, a feed-forward model for 3D scene reconstruction that aims to address the longstanding trade-off between plausible view generation for unobserved regions and geometric consistency, providing both geometrically aligned novel views and sharp depth estimates. Our approach builds on 3D Gaussian splatting (3DGS) as an intermediate differentiable scene representation and integrates it with a multi-view latent diffusion model (MV-LDM) trained to act simultaneously as a refiner and an inpainter for appearance and scene geometry. We enforce geometric consistency by guiding the diffusion process with variational 3D latent features for appearance and geometry, encoded by the feed-forward 3DGS representation and rasterized to 2D latent space. ReconSplat produces both photorealistic novel views and accurate depth maps on real-world benchmarks, RealEstate10K and DL3DV-10K, outperforming existing methods in challenging extrapolation setups. Notably, ReconSplat allows the extrapolation of unseen and challenging viewpoints jointly with coherent and precise scene geometry.

cs.CV↗

arXiv2026

A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such as Cityscapes, where differences in architecture, vegetation, object appearance, and camera characteristics limit downstream performance. Closing this gap with more detailed 3D modelling would require expensive asset and scene design, defeating the purpose of low-cost labelled data. To address this, we present a new framework that adapts an off-the-shelf diffusion model to a target domain using only imperfect pseudo-labels. Once trained, it generates high-fidelity, target-aligned images from semantic maps of any synthetic dataset, including low-effort sources created in hours rather than months. The method filters suboptimal generations, rectifies image-label misalignments, and standardises semantics across datasets, transforming weak synthetic data into competitive real-domain training sets. Experiments on five synthetic datasets and two real target datasets show segmentation gains of up to +8.0%pt. mIoU over state-of-the-art translation methods, making rapidly constructed synthetic datasets as effective as high-effort, time-intensive synthetic datasets requiring extensive manual design. This work highlights a valuable collaborative paradigm where fast semantic prototyping, combined with generative models, enables scalable, high-quality training data creation for urban scene understanding.

cs.CV↗

arXiv2026

Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos

Procedure planning seeks to estimate a sequence of actions to transition from an observed initial state to a given goal state. Current procedure planning approaches directly predict action sequences from latent representations using feed-forward neural networks or diffusion-based inference. These paradigms treat every action as plausible, lacking the ability to enforce task-specific logical constraints that render certain actions irrelevant or not plausible. We propose CEFITO, a procedure planning approach that learns a predictor to express an action-conditioned representation space. Based on this representation space, we formulate procedure planning as a task-constrained optimization problem. Unlike prior methods, CEFITO explicitly reasons over the action space by omitting irrelevant actions during inference-time planning. This reformulation enables effective procedure planning and achieves state-of-the-art accuracy on two established procedure planning benchmarks.

cs.CV↗

arXiv2026

LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection

Real-time monocular 3D object detection remains challenging due to severe depth ambiguity, viewpoint shifts, and the high computational cost of 3D reasoning. Existing approaches either rely on LiDAR or geometric priors to compensate for missing depth or sacrifice efficiency to achieve competitive accuracy. We introduce LeAD-M3D, a monocular 3D detector that achieves state-of-the-art accuracy and real-time inference without extra modalities. Our method is enabled by three key components. Asymmetric Augmentation Denoising Distillation (A2D2) transfers geometric knowledge from a clean-image teacher to a MixUp-noised student via a quality- and importance-weighted depth-feature loss, enabling stronger depth reasoning without LiDAR. 3D-aware Consistent Matching (CM$_{\text{3D}}$) improves prediction-to-ground truth assignment by integrating 3D MGIoU into the matching score, yielding stable and precise supervision. Finally, Confidence-Gated 3D Inference (CGI$_{\text{3D}}$) accelerates inference by restricting expensive 3D regression to confident regions. Together, these contributions set a new Pareto frontier for monocular 3D detection: LeAD-M3D achieves state-of-the-art accuracy on KITTI and Waymo, and the best reported car AP on Rope3D, while running up to 3.6$\,\times$ faster than prior high-accuracy models (e.g., MonoDiff). LeAD-M3D demonstrates that high fidelity and real-time monocular 3D detection is simultaneously attainable, without LiDAR, stereo, or strong geometric assumptions.

cs.CV↗

arXiv2026

MUFASA: A Multi-Layer Framework for Slot Attention

Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vectors, called slots. Current methods obtain these slot representations solely from the last layer of a pre-trained vision transformer (ViT), ignoring valuable, semantically rich information encoded across the other layers. To better utilize this latent semantic information, we introduce MUFASA, a lightweight plug-and-play framework for slot-attention-based approaches to unsupervised object segmentation. Our model computes slot attention across multiple feature layers of the ViT encoder, fully leveraging their semantic richness. We propose a fusion strategy to aggregate slots obtained on multiple layers into a unified object-centric representation. Integrating MUFASA into existing OCL methods improves their segmentation results across multiple datasets, setting a new state of the art while simultaneously improving training convergence with only minor inference overhead.

cs.CV↗

arXiv2026

Scene-Centric Unsupervised Video Panoptic Segmentation

Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task setting of unsupervised VPS, omitting any human supervision. Existing unsupervised scene understanding works mainly focused on image segmentation tasks; the video domain remains underexplored. We propose VideoCUPS, the first unsupervised VPS approach. VideoCUPS generates temporally consistent panoptic video pseudo-labels from scene-centric videos by exploiting unsupervised depth, motion, and visual cues. Training on these pseudo-labels using a novel Video DropLoss yields an accurate, unsupervised VPS model. To benchmark progress, we introduce a comprehensive evaluation protocol and four competitive baselines, extending state-of-the-art unsupervised panoptic image and instance video segmentation models to VPS. VideoCUPS outperforms all baselines and demonstrates strong label-efficient learning. With VideoCUPS, our evaluation protocol, and baselines, we provide a strong foundation for future research on unsupervised VPS.

cs.CV↗

arXiv2026

What is Missing? Explaining Neurons Activated by Absent Concepts

Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically by estimating a simplified causal structure of the model. In existing work, this causal structure often includes relationships where the presence of a concept is associated with a strong activation of a neuron. For example, attribution methods primarily identify input pixels that contribute most to a prediction, and feature visualization methods reveal inputs that cause high activation of a target neuron - the former implicitly assuming that the relevant information resides in the input, and the latter that neurons encode the presence of concepts. However, a largely overlooked type of causal relationship is that of encoded absences, where the absence of a concept increases neural activation. In this work, we show that such missing but relevant concepts are common and that mainstream XAI methods struggle to reveal them when applied in their standard form. To address this, we propose two simple extensions to attribution and feature visualization techniques that uncover encoded absences. Across experiments, we show how mainstream XAI methods can be used to reveal and explain encoded absences, how ImageNet models exploit them, and that debiasing can be improved when considering them.

cs.CV↗

arXiv2026

MARCO: Navigating the Unseen Space of Semantic Correspondence

Recent advances in semantic correspondence rely on dual-encoder architectures, combining DINOv2 with diffusion backbones. While accurate, these billion-parameter models generalize poorly beyond training keypoints, revealing a gap between benchmark performance and real-world usability, where queried points rarely match those seen during training. Building upon DINOv2, we introduce MARCO, a unified model for generalizable correspondence driven by a novel training framework that enhances both fine-grained localization and semantic generalization. By coupling a coarse-to-fine objective that refines spatial precision with a self-distillation framework, which expands sparse supervision beyond annotated regions, our approach transforms a handful of keypoints into dense, semantically coherent correspondences. MARCO sets a new state of the art on SPair-71k, AP-10K, and PF-PASCAL, with gains that amplify at fine-grained localization thresholds (+8.9 PCK@0.01), strongest generalization to unseen keypoints (+5.1, SPair-U) and categories (+4.7, MP-100), while remaining 3x smaller and 10x faster than diffusion-based approaches. Code is available at https://github.com/visinf/MARCO .

cs.CV↗

arXiv2026

INSID3: Training-Free In-Context Segmentation with DINOv3

In-context segmentation (ICS) aims to segment arbitrary concepts, e.g., objects, parts, or personalized instances, given one annotated visual examples. Existing work relies on (i) fine-tuning vision foundation models (VFMs), which improves in-domain results but harms generalization, or (ii) combines multiple frozen VFMs, which preserves generalization but yields architectural complexity and fixed segmentation granularities. We revisit ICS from a minimalist perspective and ask: Can a single self-supervised backbone support both semantic matching and segmentation, without any supervision or auxiliary models? We show that scaled-up dense self-supervised features from DINOv3 exhibit strong spatial structure and semantic correspondence. We introduce INSID3, a training-free approach that segments concepts at varying granularities only from frozen DINOv3 features, given an in-context example. INSID3 achieves state-of-the-art results across one-shot semantic, part, and personalized segmentation, outperforming previous work by +7.5 % mIoU, while using 3x fewer parameters and without any mask or category-level supervision. Code is available at https://github.com/visinf/INSID3 .

cs.CV↗

arXiv2026

Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?

Deep learning has become an essential part of computer vision, with deep neural networks (DNNs) excelling in predictive performance. However, they often fall short in other critical quality dimensions, such as robustness, calibration, or fairness. While existing studies have focused on a subset of these quality dimensions, none have explored a more general form of "well-behavedness" of DNNs. With this work, we address this gap by simultaneously studying nine different quality dimensions for image classification. Through a large-scale study, we provide a bird's-eye view by analyzing 326 backbone models and how different training paradigms and model architectures affect these quality dimensions. We reveal various new insights such that (i) vision-language models exhibit high class balance on ImageNet-1k classification and strong robustness against domain changes; (ii) training models initialized with weights obtained through self-supervised learning is an effective strategy to improve most considered quality dimensions; and (iii) the training dataset size is a major driver for most of the quality dimensions. We conclude our study by introducing the QUBA score (Quality Understanding Beyond Accuracy), a novel metric that ranks models across multiple dimensions of quality, enabling tailored recommendations based on specific user needs.

cs.CV↗

arXiv2026

Evaluating Object-Centric Models beyond Object Discovery

Object-centric learning (OCL) aims to learn structured scene representations that support compositional generalization and robustness to out-of-distribution (OOD) data. However, OCL models are often not evaluated regarding these goals. Instead, most prior work focuses on evaluating OCL models solely through object discovery and simple reasoning tasks, such as probing the representation via image classification. We identify two limitations in existing benchmarks: (1) They provide limited insights on the representation usefulness of OCL models, and (2) localization and representation usefulness are assessed using disjoint metrics. To address (1), we use instruction-tuned VLMs as evaluators, enabling scalable benchmarking across diverse VQA datasets to measure how well VLMs leverage OCL representations for complex reasoning tasks. To address (2), we introduce a unified evaluation task and metric that jointly assess localization (where) and representation usefulness (what), thereby eliminating inconsistencies introduced by disjoint evaluation. Finally, we include a simple multi-feature reconstruction baseline as a reference point.

cs.CV↗

arXiv2025

Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model

Omnidirectional depth perception is essential for mobile robotics applications that require scene understanding across a full 360° field of view. Camera-based setups offer a cost-effective option by using stereo depth estimation to generate dense, high-resolution depth maps without relying on expensive active sensing. However, existing omnidirectional stereo matching approaches achieve only limited depth accuracy across diverse environments, depth ranges, and lighting conditions, due to the scarcity of real-world data. We present DFI-OmniStereo, a novel omnidirectional stereo matching method that leverages a large-scale pre-trained foundation model for relative monocular depth estimation within an iterative optimization-based stereo matching architecture. We introduce a dedicated two-stage training strategy to utilize the relative monocular depth features for our omnidirectional stereo matching before scale-invariant fine-tuning. DFI-OmniStereo achieves state-of-the-art results on the real-world Helvipad dataset, reducing disparity MAE by approximately 16% compared to the previous best omnidirectional stereo method.

cs.CV↗

arXiv2025

Removing Cost Volumes from Optical Flow Estimators

Cost volumes are used in every modern optical flow estimator, but due to their computational and space complexity, they are often a limiting factor regarding both processing speed and the resolution of input frames. Motivated by our empirical observation that cost volumes lose their importance once all other network parts of, e.g., a RAFT-based pipeline have been sufficiently trained, we introduce a training strategy that allows removing the cost volume from optical flow estimators throughout training. This leads to significantly improved inference speed and reduced memory requirements. Using our training strategy, we create three different models covering different compute budgets. Our most accurate model reaches state-of-the-art accuracy while being $1.2\times$ faster and having a $6\times$ lower memory footprint than comparable models; our fastest model is capable of processing Full HD frames at $20\,\mathrm{FPS}$ using only $500\,\mathrm{MB}$ of GPU memory.

cs.CV↗

arXiv2025

Hardware-Efficient Cognitive Radar: Multi-Target Detection with RL-Driven Transmissive RIS

Cognitive radar has emerged as a key paradigm for next-generation sensing, enabling adaptive, intelligent operation in dynamic and complex environments. Yet, conventional cognitive multiple-input multiple-output (MIMO) radars offer strong detection performance but suffer from high hardware complexity and power demands. To overcome these limitations, we develop a reinforcement learning (RL)-based framework that leverages a transmissive reconfigurable intelligent surface (TRIS) for adaptive beamforming. A state-action-reward-state-action (SARSA) agent tunes TRIS phase shifts to improve multi-target detection in low signal-to-noise ratio (SNR) conditions while operating with far fewer radio frequency (RF) chains. Simulations confirm that the proposed TRIS-RL radar matches or, for large number of elements, even surpasses MIMO performance with reduced cost and energy requirements.

eess.SP↗

arXiv2025

Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery

Unsupervised multi-object discovery (MOD) aims to detect and localize distinct object instances in visual scenes without any form of human supervision. Recent approaches leverage object-centric learning (OCL) and motion cues from video to identify individual objects. However, these approaches use supervision to generate pseudo labels to train the OCL model. We address this limitation with MR-DINOSAUR -- Motion-Refined DINOSAUR -- a minimalistic unsupervised approach that extends the self-supervised pre-trained OCL model, DINOSAUR, to the task of unsupervised multi-object discovery. We generate high-quality unsupervised pseudo labels by retrieving video frames without camera motion for which we perform motion segmentation of unsupervised optical flow. We refine DINOSAUR's slot representations using these pseudo labels and train a slot deactivation module to assign slots to foreground and background. Despite its conceptual simplicity, MR-DINOSAUR achieves strong multi-object discovery results on the TRI-PD and KITTI datasets, outperforming the previous state of the art despite being fully unsupervised.

cs.CV↗