arXiv subjects

Computer vision

Explore arXiv computer-vision papers and cs.CV metadata. Search within the index for image segmentation, object detection and visual representation learning.

Follow this topic with RSS

At least 433 records · Page 24Linked to original sources

arXiv2025

Impact of Layer Norm on Memorization and Generalization in Transformers

Layer Normalization (LayerNorm) is one of the fundamental components in transformers that stabilizes training and improves optimization. In recent times, Pre-LayerNorm transformers have become the preferred choice over Post-LayerNorm transformers due to their stable gradient flow. However, the impact of LayerNorm on learning and memorization across these architectures remains unclear. In this work, we investigate how LayerNorm influences memorization and learning for Pre- and Post-LayerNorm transformers. We identify that LayerNorm serves as a key factor for stable learning in Pre-LayerNorm transformers, while in Post-LayerNorm transformers, it impacts memorization. Our analysis reveals that eliminating LayerNorm parameters in Pre-LayerNorm models exacerbates memorization and destabilizes learning, while in Post-LayerNorm models, it effectively mitigates memorization by restoring genuine labels. We further precisely identify that early layers LayerNorm are the most critical over middle/later layers and their influence varies across Pre and Post LayerNorm models. We have validated it through 13 models across 6 Vision and Language datasets. These insights shed new light on the role of LayerNorm in shaping memorization and learning in transformers.

cs.LG↗

arXiv2025

From 2D to 3D Without Extra Baggage: Data-Efficient Cancer Detection in Digital Breast Tomosynthesis

Digital Breast Tomosynthesis (DBT) enhances finding visibility for breast cancer detection by providing volumetric information that reduces the impact of overlapping tissues; however, limited annotated data has constrained the development of deep learning models for DBT. To address data scarcity, existing methods attempt to reuse 2D full-field digital mammography (FFDM) models by either flattening DBT volumes or processing slices individually, thus discarding volumetric information. Alternatively, 3D reasoning approaches introduce complex architectures that require more DBT training data. Tackling these drawbacks, we propose M&M-3D, an architecture that enables learnable 3D reasoning while remaining parameter-free relative to its FFDM counterpart, M&M. M&M-3D constructs malignancy-guided 3D features, and 3D reasoning is learned through repeatedly mixing these 3D features with slice-level information. This is achieved by modifying operations in M&M without adding parameters, thus enabling direct weight transfer from FFDM. Extensive experiments show that M&M-3D surpasses 2D projection and 3D slice-based methods by 11-54% for localization and 3-10% for classification. Additionally, M&M-3D outperforms complex 3D reasoning variants by 20-47% for localization and 2-10% for classification in the low-data regime, while matching their performance in high-data regime. On the popular BCS-DBT benchmark, M&M-3D outperforms previous top baseline by 4% for classification and 10% for localization.

cs.CV↗

arXiv2025

Multitask GLocal OBIA-Mamba for Sentinel-2 Landcover Mapping

Although Sentinel-2 based land use and land cover (LULC) classification is critical for various environmental monitoring applications, it is a very difficult task due to some key data challenges (e.g., spatial heterogeneity, context information, signature ambiguity). This paper presents a novel Multitask Glocal OBIA-Mamba (MSOM) for enhanced Sentinel-2 classification with the following contributions. First, an object-based image analysis (OBIA) Mamba model (OBIA-Mamba) is designed to reduce redundant computation without compromising fine-grained details by using superpixels as Mamba tokens. Second, a global-local (GLocal) dual-branch convolutional neural network (CNN)-mamba architecture is designed to jointly model local spatial detail and global contextual information. Third, a multitask optimization framework is designed to employ dual loss functions to balance local precision with global consistency. The proposed approach is tested on Sentinel-2 imagery in Alberta, Canada, in comparison with several advanced classification approaches, and the results demonstrate that the proposed approach achieves higher classification accuracy and finer details that the other state-of-the-art methods.

cs.CV↗

arXiv2025

Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals

Large Vision-Language Models (VLMs) excel at understanding and generating video descriptions but their high memory, computation, and deployment demands hinder practical use particularly for blind and low-vision (BLV) users who depend on detailed, context-aware descriptions. To study the effect of model size on accessibility-focused description quality, we evaluate SmolVLM2 variants with 500M and 2.2B parameters across two diverse datasets: AVCaps (outdoor), and Charades (indoor). In this work, we introduce two novel evaluation frameworks specifically designed for BLV accessibility assessment: the Multi-Context BLV Framework evaluating spatial orientation, social interaction, action events, and ambience contexts; and the Navigational Assistance Framework focusing on mobility-critical information. Additionally, we conduct a systematic evaluation of four different prompt design strategies and deploy both models on a smartphone, evaluating FP32 and INT8 precision variants to assess real-world performance constraints on resource-limited mobile devices.

cs.CV↗

arXiv2026

GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light & Camera

Inverse rendering of indoor scenes remains challenging due to the ambiguity between reflectance and lighting, exacerbated by inter-reflections among multiple objects. While natural illumination-based methods struggle to resolve this ambiguity, co-located light-camera setups offer better disentanglement as lighting can be easily calibrated via Structure-from-Motion. However, such setups introduce additional complexities like strong inter-reflections, dynamic shadows, near-field lighting, and moving specular highlights, which existing approaches fail to handle. We present GLOW, a Global Illumination-aware Inverse Rendering framework designed to address these challenges. GLOW integrates a neural implicit surface representation with a neural radiance cache to approximate global illumination, jointly optimizing geometry and reflectance through carefully designed regularization and initialization. We then introduce a dynamic radiance cache that adapts to sharp lighting discontinuities from near-field motion, and a surface-angle-weighted radiometric loss to suppress specular artifacts common in flashlight captures. Experiments show that GLOW substantially outperforms prior methods in material reflectance estimation under both natural and co-located illumination.

cs.CV↗

arXiv2026

SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy

Volume microscopy, including electron and light microscopy, suffers from severe anisotropic resolution due to physical axial sectioning. Existing self-supervised axial super-resolution (ASR) methods face a trilemma bounded by overly smoothed regression textures, structural hallucinations of pure diffusion models, and prohibitive inference latency. In this paper, we propose Skeleton-refinE Microscopy (SkelEM), a self-supervised framework that decouples ASR at the training-signal level: a frozen topological network and a diffusion refiner are optimized by disjoint objectives, separating low-frequency topology formulation from high-frequency detail enhancement. Building on this deterministic skeleton, we exploit a unified cycle-consistent mechanism on input sparse slices to simultaneously extract a real-domain residual prior and bidirectionally align the diffusion refiner, washing away cross-plane artifacts without synthetic bias. By truncating the reverse diffusion process with this physical prior, SkelEM achieves high-fidelity detail restoration in merely $\le 5$ steps. To rigorously assess cross-instrument generalization, we further introduce BRAVE-ASR, a new benchmark of co-aligned anisotropic and isotropic volumes acquired on a Plasma-FIB instrument. Across public benchmarks, SkelEM achieves the most favorable balance across the fidelity-perception trade-off among self-supervised methods, with state-of-the-art downstream membrane segmentation performance and robust zero-shot generalization across distinct modalities.

cs.CV↗

arXiv2026

Shell-Supervised Gaussian Splatting for Urban Real-to-Sim Reconstruction

Real-to-sim reconstruction for embodied AI requires geometry that is useful for collision reasoning, navigation, and agent-environment interaction, not only photorealistic novel-view synthesis. However, close-range urban facades are difficult for video-to-3D reconstruction: glass, reflections, repeated windows, and weak texture can produce visually plausible renderings with unstable surface geometry. We introduce shell-supervised Gaussian Splatting, a reconstruction-stage framework that uses an external facade structural shell as lightweight geometric supervision for video-driven Gaussian reconstruction. The method aligns an exterior shell to the video reconstruction frame, renders per-view depth, camera-space normal, and valid-mask maps, and applies these cues through mask-gated losses during Gaussian optimization. This design preserves RGB-driven appearance while regularizing only visible shell-supported facade regions. Experiments on anonymized close-range urban facade scenes show improved facade orientation and visible-surface point-cloud consistency over photo-only, monocular-cue, and surface-oriented Gaussian baselines, while maintaining comparable held-out rendering quality.

cs.CV↗

arXiv2026

EmoteGPT: 3D Human Facial Expressions from Natural Language Descriptions

Precise control of 3D facial expressions from text is crucial for virtual avatars, animation, and human-computer interaction, yet existing text-to-3D methods jointly generate identity, expression, and texture, making fine-grained expression control difficult. We instead formulate text-driven expression synthesis as a regression problem in the disentangled parameter space of a 3D Morphable Model (3DMM). This setting, however, requires paired data linking detailed language to precise expression parameters, which are missing from existing resources. To fill this gap, we introduce Txt2Emote, a benchmark of diverse 3D facial expressions with fine-grained textual annotations obtained from GPT-4o and a high-fidelity face tracker, providing both explicit descriptions detailing facial features and implicit descriptions referencing the situational context behind the expression. Leveraging this dataset, we present EmoteGPT, a text-to-3D expression framework based on a Multimodal Large Language Model (MLLM) with a dedicated token to semantically ground expression representations, which are then decoded into 3DMM parameters. We further improve EmoteGPT by augmenting training with large-scale image-to-3DMM data, enabling it to surpass state-of-the-art text-to-3D face synthesis methods on emotion recognition metrics and in perceived expressiveness. Integrated into avatar pipelines, our method enables photorealistic and stylized 3D avatars, as well as expressive 3D-consistent 2D face synthesis from textual input.

cs.CV↗

arXiv2026

Honeycomb: Constant-Size Scene Memory Representation for Video World Models

Video world models require persistent scene memory to maintain consistency during long-horizon video generation. Existing spatial memory systems accumulate RGB observations or latent features, causing storage requirements to grow as generation proceeds. We introduce **Honeycomb**, a video world model built on **HexMemory**, a compact low-rank representation that stores scene features in a fixed-size memory comprising six spatial and spatiotemporal planes. A feed-forward writer maps each newly generated video chunk to plane features. As the spatial coverage or temporal range expands, HexMemory warps the existing planes while preserving their dimensions, then integrates new features through confidence-weighted pooling and a learned residual correction. A reader retrieves latent features from HexMemory to condition subsequent video generation. Because the writer processes only observations from the latest chunk, Honeycomb avoids per-scene optimization and repeated processing of the full generation history. Experiments on WorldScore and RealEstate10K demonstrate strong video generation quality and robust consistency when revisiting previously observed regions, while maintaining constant feature-storage requirements throughout generation. Code and additional visualizations are available on our https://jackswl.github.io/honeycomb/.

cs.CV↗

arXiv2013

Contextually learnt detection of unusual motion-based behaviour in crowded public spaces

In this paper we are interested in analyzing behaviour in crowded public places at the level of holistic motion. Our aim is to learn, without user input, strong scene priors or labelled data, the scope of "normal behaviour" for a particular scene and thus alert to novelty in unseen footage. The first contribution is a low-level motion model based on what we term tracklet primitives, which are scene-specific elementary motions. We propose a clustering-based algorithm for tracklet estimation from local approximations to tracks of appearance features. This is followed by two methods for motion novelty inference from tracklet primitives: (a) we describe an approach based on a non-hierarchial ensemble of Markov chains as a means of capturing behavioural characteristics at different scales, and (b) a more flexible alternative which exhibits a higher generalizing power by accounting for constraints introduced by intentionality and goal-oriented planning of human motion in a particular scene. Evaluated on a 2h long video of a busy city marketplace, both algorithms are shown to be successful at inferring unusual behaviour, the latter model achieving better performance for novelties at a larger spatial scale.

cs.CV↗

arXiv2013

Multiple-object tracking in cluttered and crowded public spaces

This paper addresses the problem of tracking moving objects of variable appearance in challenging scenes rich with features and texture. Reliable tracking is of pivotal importance in surveillance applications. It is made particularly difficult by the nature of objects encountered in such scenes: these too change in appearance and scale, and are often articulated (e.g. humans). We propose a method which uses fast motion detection and segmentation as a constraint for both building appearance models and their robust propagation (matching) in time. The appearance model is based on sets of local appearances automatically clustered using spatio-kinetic similarity, and is updated with each new appearance seen. This integration of all seen appearances of a tracked object makes it extremely resilient to errors caused by occlusion and the lack of permanence of due to low data quality, appearance change or background clutter. These theoretical strengths of our algorithm are empirically demonstrated on two hour long video footage of a busy city marketplace.

cs.CV↗

arXiv2013

Quaternion Fourier Transform on Quaternion Fields and Generalizations

We treat the quaternionic Fourier transform (QFT) applied to quaternion fields and investigate QFT properties useful for applications. Different forms of the QFT lead us to different Plancherel theorems. We relate the QFT computation for quaternion fields to the QFT of real signals. We research the general linear ($GL$) transformation behavior of the QFT with matrices, Clifford geometric algebra and with examples. We finally arrive at wide-ranging non-commutative multivector FT generalizations of the QFT. Examples given are new volume-time and spacetime algebra Fourier transformations.

math.RA↗

arXiv2013

A Semi-automated Statistical Algorithm for Object Separation

We explicate a semi-automated statistical algorithm for object identification and segregation in both gray scale and color images. The algorithm makes optimal use of the observation that definite objects in an image are typically represented by pixel values having narrow Gaussian distributions about characteristic mean values. Furthermore, for visually distinct objects, the corresponding Gaussian distributions have negligible overlap with each other and hence the Mahalanobis distance between these distributions are large. These statistical facts enable one to sub-divide images into multiple thresholds of variable sizes, each segregating similar objects. The procedure incorporates the sensitivity of human eye to the gray pixel values into the variable threshold size, while mapping the Gaussian distributions into localized δ-functions, for object separation. The effectiveness of this recursive statistical algorithm is demonstrated using a wide variety of images.

cs.CV↗

arXiv2022

Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales

The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels. Scale invariance can then, in principle, be achieved by using weight sharing between the scale channels together with max or average pooling over the outputs from the scale channels. The ability of such scale channel networks to generalise to scales not present in the training set over significant scale ranges has, however, not previously been explored. In this paper, we present a systematic study of this methodology by implementing different types of scale channel networks and evaluating their ability to generalise to previously unseen scales. We develop a formalism for analysing the covariance and invariance properties of scale channel networks, and explore how different design choices, unique to scaling transformations, affect the overall performance of scale channel networks. We first show that two previously proposed scale channel network designs do not generalise well to scales not present in the training set. We explain theoretically and demonstrate experimentally why generalisation fails in these cases. We then propose a new type of foveated scale channel architecture}, where the scale channels process increasingly larger parts of the image with decreasing resolution. This new type of scale channel network is shown to generalise extremely well, provided sufficient image resolution and the absence of boundary effects. Our proposed FovMax and FovAvg networks perform almost identically over a scale range of 8, also when training on single scale training data, and do also give improved performance when learning from datasets with large scale variations in the small sample regime.

cs.CV↗

arXiv2026

Logarithmic Mathematical Morphology: Theory and applications

In Mathematical Morphology for grey-level functions, an image is analysed by another image named the structuring function. This structuring function is translated over the image domain and summed to the image. However, in an image presenting lighting variations, when the structuring function is added to this image, the amplitude of this translated structuring function should vary according to the image intensity. Such a property is not verified in Mathematical Morphology for grey level functions, when the structuring function is summed to the image with the usual additive law. This issue has been addressed by defining a framework that uses an additive law, for which the amplitude of the structuring function added to the image varies according to the amplitude of the image itself. This additive law is chosen within the Logarithmic Image Processing framework and models the lighting variations with a physical cause such as a change of light intensity. The framework is named Logarithmic Mathematical Morphology (LMM) and allows the definition of operators which are robust to such lighting variations.

eess.IV↗

arXiv2013

Discriminative extended canonical correlation analysis for pattern set matching

In this paper we address the problem of matching sets of vectors embedded in the same input space. We propose an approach which is motivated by canonical correlation analysis (CCA), a statistical technique which has proven successful in a wide variety of pattern recognition problems. Like CCA when applied to the matching of sets, our extended canonical correlation analysis (E-CCA) aims to extract the most similar modes of variability within two sets. Our first major contribution is the formulation of a principled framework for robust inference of such modes from data in the presence of uncertainty associated with noise and sampling randomness. E-CCA retains the efficiency and closed form computability of CCA, but unlike it, does not possess free parameters which cannot be inferred directly from data (inherent data dimensionality, and the number of canonical correlations used for set similarity computation). Our second major contribution is to show that in contrast to CCA, E-CCA is readily adapted to match sets in a discriminative learning scheme which we call discriminative extended canonical correlation analysis (DE-CCA). Theoretical contributions of this paper are followed by an empirical evaluation of its premises on the task of face recognition from sets of rasterized appearance images. The results demonstrate that our approach, E-CCA, already outperforms both CCA and its quasi-discriminative counterpart constrained CCA (C-CCA), for all values of their free parameters. An even greater improvement is achieved with the discriminative variant, DE-CCA.

cs.CV↗

arXiv2010

Characterizing Complex Particle Morphologies Through Shape Matching: Descriptors, Applications, and Algorithms

Many standard structural quantities, such as order parameters and correlation functions, exist for common condensed matter systems, such as spherical and rod-like particles. However, these structural quantities are often insufficient for characterizing the unique and highly complex structures often encountered in the emerging field of nano and microscale self-assembly, or other disciplines involving complex structures such as computational biology. Computer science algorithms known as "shape matching" methods pose a unique solution to this problem by providing robust metrics for quantifying the similarity between pairs of arbitrarily complex structures. This pairwise matching operation, either implicitly or explicitly, lies at the heart of most standard structural characterization schemes for particle systems. By substituting more robust "shape descriptors" into these schemes we extend their applicability to structures formed from more complex building blocks. Here, we describe several structural characterization schemes and shape descriptors that can be used to obtain various types of structural information about particle systems. We demonstrate the application of shape matching algorithms to a variety of example problems, for topics including local and global structure identification and classification, automated phase diagram mapping, and the construction of spatial and temporal correlation functions. The methods are applicable to a wide range of systems, both simulated and experimental, provided particle positions are known or can be accurately imaged.

cond-mat.soft↗

arXiv2023

Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instances

Modern Generative Adversarial Networks (GANs) generate realistic images remarkably well. Previous work has demonstrated the feasibility of "GAN-classifiers" that are distinct from the co-trained discriminator, and operate on images generated from a frozen GAN. That such classifiers work at all affirms the existence of "knowledge gaps" (out-of-distribution artifacts across samples) present in GAN training. We iteratively train GAN-classifiers and train GANs that "fool" the classifiers (in an attempt to fill the knowledge gaps), and examine the effect on GAN training dynamics, output quality, and GAN-classifier generalization. We investigate two settings, a small DCGAN architecture trained on low dimensional images (MNIST), and StyleGAN2, a SOTA GAN architecture trained on high dimensional images (FFHQ). We find that the DCGAN is unable to effectively fool a held-out GAN-classifier without compromising the output quality. However, StyleGAN2 can fool held-out classifiers with no change in output quality, and this effect persists over multiple rounds of GAN/classifier training which appears to reveal an ordering over optima in the generator parameter space. Finally, we study different classifier architectures and show that the architecture of the GAN-classifier has a strong influence on the set of its learned artifacts.

cs.LG↗