Searcharxiv⌕ Search

arXiv subjects

Stefano Gasperini

Publications and source records attributed to Stefano Gasperini.

At least 19 recordsLinked to original sources
arXiv2026

P-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive Architecture

The increasing maturity of embodied AI platforms has driven a growing interest in procedural video representation learning to support intelligent assistance systems for complex, multi-step tasks. Leveraging large-scale latent predictive training, video foundation models capture video dynamics, enabling downstream tasks such as activity understanding, spatiotemporal localization, and predictive control. However, procedural videos include actions with long-range dependencies that these models do not support, due to the quadratic complexity of self-attention. Distinct actions, for example, may be visually similar despite appearing at different points in the procedure, such as turning the stove on versus off. Here, we propose a backbone-agnostic approach that learns long-duration video representations by reducing the problem to a dense, frame-aligned action space and predicting pooled masked latent vectors. This approach allows our Procedural Joint Embedding Predictive Architecture (P-JEPA) to ingest videos over 30 minutes long, enabling effective long-form understanding of procedural steps. We evaluate P-JEPA using features extracted with VJEPA2.1, TSM, and I3D over the EgoExo4D, EgoProceL, and Assembly101 datasets, finding that it consistently improves linear separability, streaming inference, and temporal action segmentation performance, achieving state-of-the-art results on EgoExo4D fine-grained action classification while using an order of magnitude fewer parameters than LLM-based methods and running in real time.

cs.CV↗
arXiv2026

Prompting Diffusion Models for Zero-Shot Instance Segmentation

Several disruptive research directions have recently emerged in computer vision, including foundation models achieving previously unseen zero-shot performance in scene understanding, even interactively, and generative models that synthesize extremely realistic images. The latter have also been shown to be highly effective in scene understanding tasks thanks to their rich priors. However, for promptable segmentation, foundation models struggle with accurately segmenting an object's region, leading to false positives and over-segmentation. Notably, early attempts that leverage generative priors use prompts only during post-processing, yielding suboptimal segments because the process is agnostic to the user input. In this paper, we target these limitations with Prompt2Seg, a spatial conditioning framework for diffusion-based segmentation. Prompt2Seg augments a frozen diffusion segmentation model with a conditioning branch. Our approach takes spatial prompts, represented as 2D Gaussians or confidence maps, as explicit input signals, training the model to respond directly to user intent. Fine-tuned on a deliberately constrained set of object categories drawn from Hypersim and Virtual KITTI 2, Prompt2Seg generalizes zero-shot to a wide range of unseen object types and visual domains. We evaluate on seven datasets ranging from standard benchmarks to more challenging domains, including paintings, egocentric views, and X-ray data. Furthermore, we demonstrate that Prompt2Seg consistently outperforms the underlying diffusion segmentation backbone across all benchmarks. Our results suggest that the rich priors encoded in generative pretraining, combined with principled spatial conditioning, offer a compelling path toward broadly generalizing interactive segmentation without large-scale mask supervision.

cs.CV↗
arXiv2026

Future Dynamic 3D Reconstruction: Toward 3D World Modeling with Disentangled Ego-Motion

Forecasting the evolution of dynamic environments is crucial for autonomous agents. While generative world models have achieved high photorealism in 2D video synthesis by mixing ego-motion and environmental dynamics within the image plane, they exhibit physical inconsistencies, such as morphing or vanishing objects, especially over long time horizons. In this paper, we propose FR3D, a world-modeling approach that predicts a persistent 3D latent representation for future dynamic 3D reconstruction. Unlike prior works that treat the world as a sequence of image-based features, FR3D explicitly decouples the 3D evolution of the scene from the agent's trajectory, treating the inferred ego-motion as a latent proxy for action. This disentanglement resolves ambiguities between self-motion and world-motion, ensuring geometric consistency into the future. Furthermore, we introduce a teacher-student distillation strategy that leverages the spatial "common sense" of off-the-shelf foundation models, leading to robust zero-shot generalization. Extensive experiments demonstrate FR3D's strong performance for future dynamic 3D reconstruction from monocular observations across multiple datasets, even 2 seconds into the future. Project page: https://fr3d-wm.github.io.

cs.CV↗
arXiv2026

SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation

Self-supervised depth estimation from monocular sequences relies on the joint learning of a depth and a pose network. Despite abundant research done to improve the depth network, efforts on the pose remain limited. In this context, even when depth is estimated up to scale, we highlight the importance of the alignment between the scene scales estimated by the pose and depth nets. Then, we introduce SA4Depth, an approach to improve this alignment and boost the depth predictions while keeping the inference time unchanged. Our proposed method uses the depth estimated during training to reproject learnable visual features across consecutive frames and refine the pose estimates by reducing feature alignment residuals. With our method, the estimated scene scales by the separate depth and pose networks are aligned, and the prediction scale consistency is improved across different sequences. Our differentiable refinement integrates seamlessly into existing self-supervised pipelines and substantially improves their depth estimates. We demonstrate this with extensive experiments both outdoors and indoors on KITTI, Cityscapes, and NYUv2. Additionally, results on KITTI Odometry confirm the effectiveness of our pose refinement. Our code is available at https://github.com/Runningchauncey/SA4Depth .

cs.CV↗
arXiv2026

OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention

Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a novel framework for open-vocabulary 3D scene understanding built upon 3D Gaussian Splatting. At the core of our method is a Gaussian Feature Field that models semantics as a continuous function of Gaussian geometry and appearance. By explicitly conditioning semantic predictions on geometric structure, this formulation strengthens the coupling between geometry and semantics, leading to improved spatial coherence across similar structures in 3D space. To further enforce object-level semantic consistency, we introduce a structured codebook that serves as a set of shared semantic primitives. Furthermore, a codebook-guided attention mechanism is proposed to retrieve language features via similarity matching between query embeddings and learned codebook entries, enabling robust open-vocabulary reasoning while reducing intra-object feature variance. Extensive experiments on standard 2D and 3D open-vocabulary benchmarks demonstrate that our method consistently outperforms prior approaches, achieving improved segmentation quality, stronger 3D semantic consistency and a semantically interpretable codebook that provides insight into the learned representation.

cs.CV↗
arXiv2025

SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors

Recent advances in dense 3D reconstruction have demonstrated strong capability in accurately capturing local geometry. However, extending these methods to incremental global reconstruction, as required in SLAM systems, remains challenging. Without explicit modeling of global geometric consistency, existing approaches often suffer from accumulated drift, scale inconsistency, and suboptimal local geometry. To address these issues, we propose SING3R-SLAM, a globally consistent Gaussian-based monocular indoor SLAM framework. Our approach represents the scene with a Global Gaussian Map that serves as a persistent, differentiable memory, incorporates local geometric reconstruction via submap-level global alignment, and leverages global map's consistency to further refine local geometry. This design enables efficient and versatile 3D mapping for multiple downstream applications. Extensive experiments show that SING3R-SLAM achieves state-of-the-art performance in pose estimation, 3D reconstruction, and novel view rendering. It improves pose accuracy by over 10%, produces finer and more detailed geometry, and maintains a compact and memory-efficient global representation on real-world datasets.

cs.CV↗
arXiv2025

Visibility-Aware Language Aggregation for Open-Vocabulary Segmentation in 3D Gaussian Splatting

Recently, distilling open-vocabulary language features from 2D images into 3D Gaussians has attracted significant attention. Although existing methods achieve impressive language-based interactions of 3D scenes, we observe two fundamental issues: background Gaussians contributing negligibly to a rendered pixel get the same feature as the dominant foreground ones, and multi-view inconsistencies due to view-specific noise in language embeddings. We introduce Visibility-Aware Language Aggregation (VALA), a lightweight yet effective method that computes marginal contributions for each ray and applies a visibility-aware gate to retain only visible Gaussians. Moreover, we propose a streaming weighted geometric median in cosine space to merge noisy multi-view features. Our method yields a robust, view-consistent language feature embedding in a fast and memory-efficient manner. VALA improves open-vocabulary localization and segmentation across reference datasets, consistently surpassing existing works. More results are available at https://vala3d.github.io

cs.CV↗
arXiv2025

GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting

3D scene reconstruction and understanding have gained increasing popularity, yet existing methods still struggle to capture fine-grained, language-aware 3D representations from 2D images. In this paper, we present GALA, a novel framework for open-vocabulary 3D scene understanding with 3D Gaussian Splatting (3DGS). GALA distills a scene-specific 3D instance feature field via self-supervised contrastive learning. To extend to generalized language feature fields, we introduce the core contribution of GALA, a cross-attention module with two learnable codebooks that encode view-independent semantic embeddings. This design not only ensures intra-instance feature similarity but also supports seamless 2D and 3D open-vocabulary queries. It reduces memory consumption by avoiding per-Gaussian high-dimensional feature learning. Extensive experiments on real-world datasets demonstrate GALA's remarkable open-vocabulary performance on both 2D and 3D.

cs.CV↗
arXiv2025

Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation

In panoptic segmentation, individual instances must be separated within semantic classes. As state-of-the-art methods rely on a pre-defined set of classes, they struggle with novel categories and out-of-distribution (OOD) data. This is particularly problematic in safety-critical applications, such as autonomous driving, where reliability in unseen scenarios is essential. We address the gap between outstanding benchmark performance and reliability by proposing Prior2Former (P2F), the first approach for segmentation vision transformers rooted in evidential learning. P2F extends the mask vision transformer architecture by incorporating a Beta prior for computing model uncertainty in pixel-wise binary mask assignments. This design enables high-quality uncertainty estimation that effectively detects novel and OOD objects enabling state-of-the-art anomaly instance segmentation and open-world panoptic segmentation. Unlike most segmentation models addressing unknown classes, P2F operates without access to OOD data samples or contrastive training on void (i.e., unlabeled) classes, making it highly applicable in real-world scenarios where such prior information is unavailable. Additionally, P2F can be flexibly applied to anomaly instance and panoptic segmentation. Through comprehensive experiments on the Cityscapes, COCO, SegmentMeIfYouCan, and OoDIS datasets, P2F demonstrates state-of-the-art performance across the board.

cs.CV↗
arXiv2025

From Open-Vocabulary to Vocabulary-Free Semantic Segmentation

Open-vocabulary semantic segmentation enables models to identify novel object categories beyond their training data. While this flexibility represents a significant advancement, current approaches still rely on manually specified class names as input, creating an inherent bottleneck in real-world applications. This work proposes a Vocabulary-Free Semantic Segmentation pipeline, eliminating the need for predefined class vocabularies. Specifically, we address the chicken-and-egg problem where users need knowledge of all potential objects within a scene to identify them, yet the purpose of segmentation is often to discover these objects. The proposed approach leverages Vision-Language Models to automatically recognize objects and generate appropriate class names, aiming to solve the challenge of class specification and naming quality. Through extensive experiments on several public datasets, we highlight the crucial role of the text encoder in model performance, particularly when the image text classes are paired with generated descriptions. Despite the challenges introduced by the sensitivity of the segmentation text encoder to false negatives within the class tagging process, which adds complexity to the task, we demonstrate that our fully automated pipeline significantly enhances vocabulary-free segmentation accuracy across diverse real-world scenarios.

cs.CV↗
arXiv2024

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians

3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While its vanilla representation is mainly designed for view synthesis, recent works extended it to scene understanding with language features. However, storing additional high-dimensional features per Gaussian for semantic information is memory-intensive, which limits their ability to segment and interpret challenging scenes. To this end, we introduce SuperGSeg, a novel approach that fosters cohesive, context-aware hierarchical scene representation by disentangling segmentation and language field distillation. SuperGSeg first employs neural 3D Gaussians to learn geometry, instance and hierarchical segmentation features from multi-view images with the aid of off-the-shelf 2D masks. These features are then leveraged to create a sparse set of \acrlong{superg}s. \acrlong{superg}s facilitate the lifting and distillation of 2D language features into 3D space. They enable hierarchical scene understanding with high-dimensional language feature rendering at moderate GPU memory costs. Extensive experiments demonstrate that SuperGSeg achieves remarkable performance on both open-vocabulary object selection and semantic segmentation tasks.

cs.CV↗
arXiv2024

Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation

Estimating the pose of objects through vision is essential to make robotic platforms interact with the environment. Yet, it presents many challenges, often related to the lack of flexibility and generalizability of state-of-the-art solutions. Diffusion models are a cutting-edge neural architecture transforming 2D and 3D computer vision, outlining remarkable performances in zero-shot novel-view synthesis. Such a use case is particularly intriguing for reconstructing 3D objects. However, localizing objects in unstructured environments is rather unexplored. To this end, this work presents Zero123-6D, the first work to demonstrate the utility of Diffusion Model-based novel-view-synthesizers in enhancing RGB 6D pose estimation at category-level, by integrating them with feature extraction techniques. Novel View Synthesis allows to obtain a coarse pose that is refined through an online optimization method introduced in this work to deal with intra-category geometric differences. In such a way, the outlined method shows reduction in data requirements, removal of the necessity of depth information in zero-shot category-level 6D pose estimation task, and increased performance, quantitatively demonstrated through experiments on the CO3D dataset.

cs.CV↗
arXiv2023

Re-Nerfing: Improving Novel View Synthesis through Novel View Synthesis

Recent neural rendering and reconstruction techniques, such as NeRFs or Gaussian Splatting, have shown remarkable novel view synthesis capabilities but require hundreds of images of the scene from diverse viewpoints to render high-quality novel views. With fewer images available, these methods start to fail since they can no longer correctly triangulate the underlying 3D geometry and converge to a non-optimal solution. These failures can manifest as floaters or blurry renderings in sparsely observed areas of the scene. In this paper, we propose Re-Nerfing, a simple and general add-on approach that leverages novel view synthesis itself to tackle this problem. Using an already trained NVS method, we render novel views between existing ones and augment the training data to optimize a second model. This introduces additional multi-view constraints and allows the second model to converge to a better solution. With Re-Nerfing we achieve significant improvements upon multiple pipelines based on NeRF and Gaussian-Splatting in sparse view settings of the mip-NeRF 360 and LLFF datasets. Notably, Re-Nerfing does not require prior knowledge or extra supervision signals, making it a flexible and practical add-on.

cs.CV↗
arXiv2023

VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis

The generation of high-fidelity view synthesis is essential for robotic navigation and interaction but remains challenging, particularly in indoor environments and real-time scenarios. Existing techniques often require significant computational resources for both training and rendering, and they frequently result in suboptimal 3D representations due to insufficient geometric structuring. To address these limitations, we introduce VoxNeRF, a novel approach that utilizes easy-to-obtain geometry priors to enhance both the quality and efficiency of neural indoor reconstruction and novel view synthesis. We propose an efficient voxel-guided sampling technique that allocates computational resources selectively to the most relevant segments of rays based on a voxel-encoded geometry prior, significantly reducing training and rendering time. Additionally, we incorporate a robust depth loss to improve reconstruction and rendering quality in sparse view settings. Our approach is validated with extensive experiments on ScanNet and ScanNet++ where VoxNeRF outperforms existing state-of-the-art methods and establishes a new benchmark for indoor immersive interpolation and extrapolation settings.

cs.CV↗
arXiv2023

3D Adversarial Augmentations for Robust Out-of-Domain Predictions

Since real-world training datasets cannot properly sample the long tail of the underlying data distribution, corner cases and rare out-of-domain samples can severely hinder the performance of state-of-the-art models. This problem becomes even more severe for dense tasks, such as 3D semantic segmentation, where points of non-standard objects can be confidently associated to the wrong class. In this work, we focus on improving the generalization to out-of-domain data. We achieve this by augmenting the training set with adversarial examples. First, we learn a set of vectors that deform the objects in an adversarial fashion. To prevent the adversarial examples from being too far from the existing data distribution, we preserve their plausibility through a series of constraints, ensuring sensor-awareness and shapes smoothness. Then, we perform adversarial augmentation by applying the learned sample-independent vectors to the available objects when training a model. We conduct extensive experiments across a variety of scenarios on data from KITTI, Waymo, and CrashD for 3D object detection, and on data from SemanticKITTI, Waymo, and nuScenes for 3D semantic segmentation. Despite training on a standard single dataset, our approach substantially improves the robustness and generalization of both 3D object detection and 3D semantic segmentation methods to out-of-domain data.

cs.CV↗
arXiv2023

Robust Monocular Depth Estimation under Challenging Conditions

While state-of-the-art monocular depth estimation approaches achieve impressive results in ideal settings, they are highly unreliable under challenging illumination and weather conditions, such as at nighttime or in the presence of rain. In this paper, we uncover these safety-critical issues and tackle them with md4all: a simple and effective solution that works reliably under both adverse and ideal conditions, as well as for different types of learning supervision. We achieve this by exploiting the efficacy of existing methods under perfect settings. Therefore, we provide valid training signals independently of what is in the input. First, we generate a set of complex samples corresponding to the normal training ones. Then, we train the model by guiding its self- or full-supervision by feeding the generated samples and computing the standard losses on the corresponding original images. Doing so enables a single model to recover information across diverse conditions without modifications at inference time. Extensive experiments on two challenging public datasets, namely nuScenes and Oxford RobotCar, demonstrate the effectiveness of our techniques, outperforming prior works by a large margin in both standard and challenging conditions. Source code and data are available at: https://md4all.github.io.

cs.CV↗
arXiv2023

Segmenting Known Objects and Unseen Unknowns without Prior Knowledge

Panoptic segmentation methods assign a known class to each pixel given in input. Even for state-of-the-art approaches, this inevitably enforces decisions that systematically lead to wrong predictions for objects outside the training categories. However, robustness against out-of-distribution samples and corner cases is crucial in safety-critical settings to avoid dangerous consequences. Since real-world datasets cannot contain enough data points to adequately sample the long tail of the underlying distribution, models must be able to deal with unseen and unknown scenarios as well. Previous methods targeted this by re-identifying already-seen unlabeled objects. In this work, we propose the necessary step to extend segmentation with a new setting which we term holistic segmentation. Holistic segmentation aims to identify and separate objects of unseen, unknown categories into instances without any prior knowledge about them while performing panoptic segmentation of known classes. We tackle this new problem with U3HS, which finds unknowns as highly uncertain regions and clusters their corresponding instance-aware embeddings into individual objects. By doing so, for the first time in panoptic segmentation with unknown objects, our U3HS is trained without unknown categories, reducing assumptions and leaving the settings as unconstrained as in real-life scenarios. Extensive experiments on public data from MS COCO, Cityscapes, and Lost&Found demonstrate the effectiveness of U3HS for this new, challenging, and assumptions-free setting called holistic segmentation. Project page: https://holisticseg.github.io.

cs.CV↗
arXiv2022

3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection

As 3D object detection on point clouds relies on the geometrical relationships between the points, non-standard object shapes can hinder a method's detection capability. However, in safety-critical settings, robustness to out-of-domain and long-tail samples is fundamental to circumvent dangerous issues, such as the misdetection of damaged or rare cars. In this work, we substantially improve the generalization of 3D object detectors to out-of-domain data by deforming point clouds during training. We achieve this with 3D-VField: a novel data augmentation method that plausibly deforms objects via vector fields learned in an adversarial fashion. Our approach constrains 3D points to slide along their sensor view rays while neither adding nor removing any of them. The obtained vectors are transferable, sample-independent and preserve shape and occlusions. Despite training only on a standard dataset, such as KITTI, augmenting with our vector fields significantly improves the generalization to differently shaped objects and scenes. Towards this end, we propose and share CrashD: a synthetic dataset of realistic damaged and rare cars, with a variety of crash scenarios. Extensive experiments on KITTI, Waymo, our CrashD and SUN RGB-D show the generalizability of our techniques to out-of-domain data, different models and sensors, namely LiDAR and ToF cameras, for both indoor and outdoor scenes. Our CrashD dataset is available at https://crashd-cars.github.io.

cs.CV↗