Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 1514 publications
A Recipe for Improving Remote Sensing Zero Shot Generalization
Aviad Barzilai
Yotam Gigi
Vered Silverman
Yehonathan Refael
Bolous Jaber
Amr Helmy
3rd ML4RS Workshop at ICLR 2025
Preview abstract
Foundation models have had a significant impact across various AI applications, enabling applications for use cases that were previously impossible. Visual language models (VLMs), in particular, have outperformed other techniques in many tasks. In remote sensing (RS), foundation models have shown improvements across various applications. However, unlike other fields, the use of VLMs with large-scale remote sensing image-text datasets remains limited.
In this work, we first introduce two novel image-caption datasets for training of remote sensing foundation models. The first dataset pairs aerial and satellite imagery, aligned with Google-Maps data, with high-quality captions generated using Gemini. The second utilizes public web images and their corresponding alt-text, filtered for only remote sensing domain, resulting in a highly diverse dataset.
We show that using these datasets to pre-train the Mammut [], a VLM architecture, results in state-of-the-art generalization performance in a zero-shot classification and cross-modal retrieval on well-known public benchmarks. Secondly, we leverage this newly pre-trained VLM to generate inference attention maps for a novel class query (i.e., a class unseen during training). We subsequently propose an iterative self-supervised fine-tuning approach where samples aligned with these attention maps are iteratively pseudo-labeled and utilized for model training.
View details
Binamix -- A Python Library for Generating Binaural Audio Datasets
Dan Barry
Davoud Shariat Panah
Alessandro Ragano
Andrew Hines
AES 158th Audio Engineering Society Convention (2025)
Preview abstract
The increasing demand for spatial audio in applications such as virtual reality, immersive media, and spatial audio research necessitates robust solutions to generate binaural audio data sets for use in testing and validation. Binamix is an open-source Python library designed to facilitate programmatic binaural mixing using the extensive SADIE II Database, which provides Head Related Impulse Response (HRIR) and Binaural Room Impulse Response (BRIR) data for 20 subjects. The Binamix library provides a flexible and repeatable framework for creating large-scale spatial audio datasets, making it an invaluable resource for codec evaluation, audio quality metric development, and machine learning model training. A range of pre-built example scripts, utility functions, and visualization plots further streamline the process of custom pipeline creation. This paper presents an overview of the library’s capabilities, including binaural rendering, impulse response interpolation, and multi-track mixing for various speaker layouts. The tools utilize a modified Delaunay triangulation technique to achieve accurate HRIR/BRIR interpolation where desired angles are not present in the data. By supporting a wide range of parameters such as azimuth, elevation, subject Impulse Responses (IRs), speaker layouts, mixing controls, and more, the library enables researchers to create large binaural datasets for any downstream purpose. Binamix empowers researchers and developers to advance spatial audio applications with reproducible methodologies by offering an open-source solution for
binaural rendering and dataset generation. We release the library under the Apache 2.0 License at https://github.com/QxLabIreland/Binamix/
View details
On the Design of the Binaural Rendering Library for Eclipsa Audio Immersive Audio Container
Tomasz Rudzki
Gavin Kearney
AES 158th Convention of the Audio Engineering Society (2025)
Preview abstract
Immersive Audio Media and Formats (IAMF), also known as Eclipsa Audio, is an open-source audio container developed to accommodate multichannel and scene-based audio formats. Headphone-based delivery of IAMF audio requires efficient binaural rendering. This paper introduces the Open Binaural Renderer (OBR), which is designed to render IAMF audio. It discusses the core rendering algorithm, the binaural filter design process as well as real-time implementation of the renderer in a form of an open-source C++ rendering library. Designed for
multi-platform compatibility, the renderer incorporates a novel approach to binaural audio processing, leveraging a combination of spherical harmonic (SH) based virtual listening room model and anechoic binaural filters. Through its design, the IAMF binaural renderer provides a robust solution for delivering high-quality immersive audio across diverse platforms and applications.
View details
Perceptual Evaluation of a Mix Presentation for Immersive Audio with IAMF
Carlos Tejeda-Ocampo
Toni Hirvonen
Ema Souza-Blanes
Mahmoud Namazi
AES 158th Convention of the Audio Engineering Society (2025)
Preview abstract
Immersive audio mix presentations involve transmitting and rendering several audio elements simultaneously. This enables next-generation applications, such as personalized playback. Using immersive loudspeaker and headphone MUSHRA tests, we investigate bitrate vs. quality for a typical mix presentation use case of a foreground stereo element, plus a background Ambisonics scene. For coding, we use Immersive Audio Model and Formats, a recently
proposed system for Next-Generation Audio. Excellent quality is achieved at 384 kbit/s even with reasonable amount of personalization. We also propose a framework for content-aware analysis that can significantly reduce the bitrate when using underlying legacy audio coding instances.
View details
Bridging Sign and Spoken Languages: Pseudo GlossGeneration for Sign Language Translation
Trevor Cohn
Jianyuan Guo
Advances in Neural Information Processing Systems (NeurIPS) (2025)
Preview abstract
Sign Language Translation (SLT) aims to map sign language videos to spoken language text. A common approach leverages gloss annotations as an intermediate representation, decomposing SLT into two sub-tasks: video-to-gloss recognition and gloss-to-text translation. While effective, this paradigm relies on expert-annotated gloss labels, which are costly and increasingly unavailable in many datasets, limiting scalability.
To address this challenge, we propose a gloss-free pseudo gloss generation framework that eliminates the need for human-annotated glosses while preserving the structured intermediate representation. Specifically, we prompt a Large Language Model (LLM) with example text-gloss pairs to extract potential sign-related gloss words from the text by leveraging its in-context learning capability.
To mitigate the inherent misalignment between generated pseudo glosses and sign sequences in the video, we further refine their order by formulating the alignment as a weakly supervised learning problem.
With the reordered pseudo-glosses, additional alignment losses such as CTC can be incorporated to enhance supervision. We train our SLT model—comprising a vision encoder and a translator—under a three-stage pipeline, effectively bridging the gap between sign and spoken language.
Despite its simplicity, our approach outperforms previous state-of-the-art gloss-free frameworks across three SLT benchmarks and achieves competitive results with gloss-based methods.
View details
Preview abstract
The dominant paradigm in image retrieval systems today is to search large databases using global image features, and re-rank those initial results with local image feature matching techniques.
This design, dubbed \emph{global-to-local}, stems from the computational cost of local matching approaches, which can only be afforded for a small number of retrieved images.
However, emerging efficient local feature search approaches have opened up new possibilities, in particular enabling detailed retrieval at large scale, to find partial matches which are often missed by global feature search.
In parallel, global feature-based re-ranking has shown promising results with high computational efficiency.
In this work, we leverage these building blocks to introduce a \emph{local-to-global} retrieval paradigm, where efficient local feature search meets effective global feature re-ranking.
Critically, we propose a re-ranking method where global features are computed on-the-fly, based on the local feature retrieval similarities.
Such re-ranking-only global features, dubbed \emph{similarity embeddings}, leverage multidimensional scaling techniques to create embeddings which respect the local similarities obtained during search, enabling a significant re-ranking boost.
Experimentally, we demonstrate unprecedented retrieval performance on the Revisited Oxford and Paris datasets, setting new state-of-the-art results.
View details
Generating Dialogues from Egocentric Instructional Videos for Task Assistance: Dataset, Method and Benchmark
Lavisha Aggarwal
Vikas Bahirwani
Lin Li
Andrea Colaco
2025
Preview abstract
Many everyday tasks ranging from fixing appliances, cooking recipes to car maintenance require expert knowledge, especially when tasks are complex and multi-step. Despite growing interest in AI agents, there is a scarcity of dialogue-video datasets grounded for real world task assistance. In this paper, we propose a simple yet effective approach that transforms single-person instructional videos into task-guidance two-person dialogues, aligned with fine grained steps and video-clips. Our fully automatic approach, powered by large language models, offers an efficient alternative to the substantial cost and effort required for manual data collection. Using this technique, we build HowToDIV, a large-scale dataset containing 507 conversations, 6636 question-answer pairs and 24 hours of videoclips across diverse tasks in cooking, mechanics, and planting. Each session includes multi-turn conversation where an expert teaches a novice user how to perform a task step by step, while observing user's surrounding through a camera and microphone equipped wearable device. We establish the baseline benchmark performance on HowToDIV dataset through Gemma-3 model, for future research on this new task of dialogues for procedural-task assistance. Our dataset and code are publicly available at our project page: https://github.com/google/howtodiv.
View details
Preview abstract
In this paper, we introduce a novel estimator for vision-aided inertial navigation systems (VINS), the Preconditioned Cholesky-based Square Root Information Filter (PC-SRIF). When working with linear systems, employing Cholesky decomposition offers superior efficiency but can compromise numerical stability. Due to this, existing VINS literature on (Square Root) Information Filters often opts for QR decomposition on platforms where single precision is preferred, avoiding the numerical challenges associated with Cholesky decomposition. While these issues are often attributed to the ill-conditioned information matrix in VINS, our analysis reveals that this is not an inherent property of VINS but rather a consequence of specific parametrizations. We identify several factors that contribute to an ill-conditioned information matrix and propose a preconditioning technique to mitigate these conditioning issues. Building on this analysis, we present PC-SRIF, which exhibits remarkable stability in performing Cholesky decomposition using single precision when solving linear systems in VINS. Consequently, PC-SRIF achieves superior theoretical efficiency compared to alternative estimators. To validate the efficiency advantages and numerical stability of PC-SRIF based VINS, we have conducted carefully controlled experiments, which provide empirical evidence in support of our theoretical findings. Empirically, in our VINS, PC-SRIF achieves more than 2x better efficiency than SRIF.
View details
Preview abstract
Large-scale video generative models, capable of creating realistic videos of diverse visual concepts, are strong candidates for general-purpose physical world simulators. However, their adherence to physical commonsense across real-world actions remains unclear (e.g., playing tennis, backflip). Existing benchmarks suffer from limitations such as limited size, lack of human evaluation, sim-to-real gaps, and absence of fine-grained physical rule analysis. To address this, we introduce VideoPhy-2, an action-centric dataset for evaluating physical commonsense in generated videos. We curate 200 diverse actions and detailed prompts for video synthesis from modern generative models. We perform human evaluation that assesses semantic adherence, physical commonsense, and grounding of physical rules in the generated videos. Our findings reveal major shortcomings, with even the best model achieving only 22% joint performance (i.e., high semantic and physical commonsense adherence) on the hard subset of VideoPhy-2. We find that the models particularly struggle with conservation laws like mass and momentum. Finally, we also train VideoPhy-AutoEval, an automatic evaluator for fast, reliable assessment on our dataset. Overall, VideoPhy-2 serves as a rigorous benchmark, exposing critical gaps in video generative models and guiding future research in physically-grounded video generation. The data and code is available at https://videophy2.github.io/
View details
Text to 3D Object Generation for Scalable Room Assembly
Sonia Laguna
Alberto García García
Marie-Julie Rakotosaona
Stylianos Moschoglou
Leonhard Helminger
2025
Preview abstract
Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenarios. To address data scarcity, an end-to-end system for synthetic data generation for scalable, high-quality, and customizable 3D indoor scenes. By integrating text-to-image and multi-view diffusion models with NeRF-based meshing, this system generates high-fidelity 3D assets from text prompts and incorporates them into pre-defined floor plans using a rendering tool, Blender. By incorporating novel loss functions and training strategies into prior existing methods, or method supports on-demand object generation, bridging the domain gap between synthetic and real-world data. This system advances synthetic data’s role in addressing machine learning training limitations, enabling more robust and generalizable models for real-world applications.
View details
LightLab: Controlling Light Sources in Images with Diffusion Models
Nadav Magar
Amir Hertz
Eric Tabellion
Alex Rav Acha
Yedid Hoshen
Arik Shamir
SIGGRAPH Conference Papers '25 (2025)
Preview abstract
We present a simple, yet effective diffusion-based method for fine-grained, parametric control over light sources in an image. Existing relighting methods either rely on multiple input views to perform inverse rendering at inference time, or fail to provide explicit control over light changes. Our method fine-tunes a diffusion model on a small set of real raw photograph pairs, supplemented by synthetically rendered images at scale, to elicit its photorealistic prior for the relighting task. We leverage the linearity of light to synthesize image pairs depicting controlled light changes of either a target light source or ambient illumination. Using this data and an appropriate fine-tuning scheme, we train a model for precise illumination changes with explicit control over light intensity and color. Lastly, we show how our method can achieve compelling light editing results, and outperforms existing methods based on user preference.
View details
RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation
Aviv Slobodkin
Hagai Taitelbaum
Brian Gordon
Michal Sokolik
Almog Gueta
Royi Rassin
Dani Lischinski
2025
Preview abstract
Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject image. Despite its broad downstream applicability - ranging from enhanced personalization in image generation to consistent character representation in video rendering - progress in this field is limited by the lack of reliable automatic evaluation. Existing methods either assess only one aspect of the task (i.e., textual alignment or subject preservation), misalign with human judgments, or rely on costly API-based evaluation. To address this gap, we introduce RefVNLI, a cost-effective metric that evaluates both textual alignment and subject preservation in a single run. Trained on a large-scale dataset derived from video-reasoning benchmarks and image perturbations, RefVNLI outperforms or statistically matches existing baselines across multiple benchmarks and subject categories (e.g., Animal, Object), achieving up to 6.4-point gains in textual alignment and 5.9-point gains in subject preservation.
View details
The JPEG XL Image Codec: History, Features, Coding Tools, Design Rationale, and Future
Jon Sneyers
Luca Versari
Zoltan Szabadka
Amnon Cohen-Tidhar
Moritz Firsching
Evgenii Kliuchnikov
Tal Lev-Ami
Eric Portis
Thomas Richter
WATANABE Osamu
arxiv (2025) (to appear)
Preview abstract
This article provides an extensive overview of the JPEG XL codec, describing its features and coding tools,
the design rationale behind it, as well as its performance, history and potential future. It can be used as a
companion document to the standard (ISO/IEC 18181), or as a standalone article to better understand the
codec, either at a high level or in considerable technical detail.
View details
Preview abstract
We present PhoMoH, a neural network methodology to construct generative models of photo-realistic 3D geometry and appearance of human heads including hair, beards, an oral cavity, and clothing. In contrast to prior work, PhoMoH models the human head using neural fields, thus supporting complex topology. Instead of learning a head model from scratch, we propose to augment an existing expressive head model with new features. Concretely, we learn a highly detailed geometry network layered on top of a mid-resolution head model together with a detailed, local geometry-aware, and disentangled color field. Our proposed architecture allows us to learn photo-realistic human head models from relatively little data. The learned generative geometry and appearance networks can be sampled individually and enable the creation of diverse and realistic human heads. Extensive experiments validate our method qualitatively and across different metrics.
View details
Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis
Winter Conference on Applications of Computer Vision 2024 (2024) (to appear)
Preview abstract
We propose Hierarchical Text Spotter (HTS), the first method for the joint task of word-level text spotting and geometric layout analysis.
HTS can annotate text in images with a hierarchical representation of 4 levels: character, word, line, and paragraph.
The proposed HTS is characterized by two novel components:
(1) a Unified-Detector-Polygon (UDP) that produces Bezier Curve polygons of text lines and an affinity matrix for paragraph grouping between detected lines;
(2) a Line-to-Character-to-Word (L2C2W) recognizer that splits lines into characters and further merges them back into words.
HTS achieves state-of-the-art results on multiple word-level text spotting benchmark datasets as well as geometric layout analysis tasks.
Code will be released upon acceptance.
View details
