Estimating camera motion in deformable scenes poses a complex and open research challenge. Most existing non-rigid structure from motion techniques assume to observe also static scene parts besides deforming scene parts in order to establish an anchoring reference. However, this assumption does not hold true in certain relevant application cases such as endoscopies. Deformable odometry and SLAM pipelines, which tackle the most challenging scenario of exploratory trajectories, suffer from a lack of robustness and proper quantitative evaluation methodologies. To tackle this issue with a common benchmark, we introduce the Drunkard's Dataset, a challenging collection of synthetic data targeting visual navigation and reconstruction in deformable environments. This dataset is the first large set of exploratory camera trajectories with ground truth inside 3D scenes where every surface exhibits non-rigid deformations over time. Simulations in realistic 3D buildings lets us obtain a vast amount of data and ground truth labels, including camera poses, RGB images and depth, optical flow and normal maps at high resolution and quality. We further present a novel deformable odometry method, dubbed the Drunkard's Odometry, which decomposes optical flow estimates into rigid-body camera motion and non-rigid scene deformations. In order to validate our data, our work contains an evaluation of several baselines as well as a novel tracking error metric which does not require ground truth data.

We tackle the task of conditional music generation. We introduce MusicGen, a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns, which eliminates the need for cascading several models, e.g., hierarchically or upsampling. Following this approach, we demonstrate how MusicGen can generate high-quality samples, both mono and stereo, while being conditioned on textual description or melodic features, allowing better controls over the generated output. We conduct extensive empirical evaluation, considering both automatic and human studies, showing the proposed approach is superior to the evaluated baselines on a standard text-to-music benchmark. Through ablation studies, we shed light over the importance of each of the components comprising MusicGen.

The flat-headed felines are the smallest wild cats in Southeast Asia. New images from Thailand's DNP and Panthera prove the existence and rediscovery of one of the world's most Endangered and least known wild cats, the flat-headed cat, in Thailand's Princess Sirindhorn Wildlife Sanctuary. Breakthroughs, discoveries, and DIY tips sent every weekday. Camera traps in Thailand have captured adorable passersby with significant implication for the country's conservation efforts. While these furry creatures might look like your average house cat, they're actually wild flat-headed cats ().

The recent advances in natural language processing (NLP), have led to a new trend of applying large language models (LLMs) to real-world scenarios. While the latest LLMs are astonishingly fluent when interacting with humans, they suffer from the misinformation problem by unintentionally generating factually false statements. This can lead to harmful consequences, especially when produced within sensitive contexts, such as healthcare. Yet few previous works have focused on evaluating misinformation in the long-form (LF) generation of LLMs, especially for knowledge-intensive topics. Moreover, although LLMs have been shown to perform well in different languages, misinformation evaluation has been mostly conducted in English.

A prototype of a Rapidus 300mm wafer displayed at the Semicon Japan exhibition. The industry ministry has earmarked ¥150 billion for state-backed chip venture Rapidus, bringing the cumulative government investment in the venture to ¥250 billion. The industry ministry is set to nearly quadruple its budgeted support for cutting-edge semiconductors and artificial-intelligence development to about ¥1.23 trillion ($7.9 billion) for the fiscal year starting in April. Overall the Ministry of Economy, Trade and Industry's budget rose by about 50% from the previous year to ¥3.07 trillion, largely due to the jump in chips and AI spending. After Prime Minister Sanae Takaichi's Cabinet signed off on it Friday, the government's initial budget plan will be debated in parliament in the new year.

The Convolutional Neural Networks (CNNs) have laid the foundation for many techniques in various applications. Despite achieving remarkable performance in some tasks, the 3D viewpoint generalizability of CNNs is still far behind humans visual capabilities. Although recent efforts, such as the Capsule Networks, have been made to address this issue, these new models are either hard to train and/or incompatible with existing CNN-based techniques specialized for different applications. Observing that humans use binocular vision to understand the world, we study in this paper whether the 3D viewpoint generalizability of CNNs can be achieved via a binocular vision. We propose CNN^{2}, a CNN that takes two images as input, which resembles the process of an object being viewed from the left eye and the right eye. CNN^{2} uses novel augmentation, pooling, and convolutional layers to learn a sense of three-dimensionality in a recursive manner. Empirical evaluation shows that CNN^{2} has improved viewpoint generalizability compared to vanilla CNNs. Furthermore, CNN^{2} is easy to implement and train, and is compatible with existing CNN-based specialized techniques for different applications.

We introduce Breaking Bad, a large-scale dataset of fractured objects. Our dataset consists of over one million fractured objects simulated from ten thousand base models. The fracture simulation is powered by a recent physically based algorithm that efficiently generates a variety of fracture modes of an object.

Text-guided image editing is widely needed in daily life, ranging from personal use to professional applications such as Photoshop.However, existing methods are either zero-shot or trained on an automatically synthesized dataset, which contains a high volume of noise.Thus, they still require lots of manual tuning to produce desirable outcomes in practice.To address this issue, we introduce MagicBrush, the first large-scale, manually annotated dataset for instruction-guided real image editing that covers diverse scenarios: single-turn, multi-turn, mask-provided, and mask-free editing.MagicBrush comprises over 10K manually annotated triplets (source image, instruction, target image), which supports trainining large-scale text-guided image editing models.We fine-tune InstructPix2Pix on MagicBrush and show that the new model can produce much better images according to human evaluation.We further conduct extensive experiments to evaluate current image editing baselines from multiple dimensions including quantitative, qualitative, and human evaluations.The results reveal the challenging nature of our dataset and the gap between current baselines and real-world editing needs.

In Onyx Tempest, I wanted to capture the intensity of a Friesian skidding into a sharp turn. The backlit dust, flying mane, and sudden shift in momentum revealed his power and control. I framed the moment to emphasize energy, contrast, and the precision of the movement. Breakthroughs, discoveries, and DIY tips sent every weekday. The reFocus Awards has announced the stunning winners of the 2025 Photographers of the Year at the World Photo Annual .

Understanding different human attributes and how they affect model behavior may become a standard need for all model creation and usage, from traditional computer vision tasks to the newest multimodal generative AI systems. In computer vision specifically, we have relied on datasets augmented with perceived attribute signals (eg, gender presentation, skin tone, and age) and benchmarks enabled by these datasets. Typically labels for these tasks come from human annotators. However, annotating attribute signals, especially skin tone, is a difficult and subjective task. Perceived skin tone is affected by technical factors, like lighting conditions, and social factors that shape an annotator's lived experience.This paper examines the subjectivity of skin tone annotation through a series of annotation experiments using the Monk Skin Tone (MST) scale~\cite{Monk2022Monk}, a small pool of professional photographers, and a much larger pool of trained crowdsourced annotators. Along with this study we release the Monk Skin Tone Examples (MST-E) dataset, containing 1515 images and 31 videos spread across the full MST scale. MST-E is designed to help train human annotators to annotate MST effectively.Our study shows that annotators can reliably annotate skin tone in a way that aligns with an expert in the MST scale, even under challenging environmental conditions. We also find evidence that annotators from different geographic regions rely on different mental models of MST categories resulting in annotations that systematically vary across regions. Given this, we advise practitioners to use a diverse set of annotators and a higher replication count for each image when annotating skin tone for fairness research.