Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
The paper introduces SoundMHPE, an encoder‑decoder framework that estimates 3D poses of multiple people using only acoustic signals. It addresses challenges such as overlapping acoustic signatures and inter‑person reflections by employing a multi‑scale acoustic encoder and a temporal pose decoder with attention. The authors created the 6‑hour Acoustic Multi‑person Pose (AMP) dataset and show that SoundMHPE outperforms baseline models.
The paper introduces E‑RGB‑D, a real‑time event‑based perception system that combines a Digital Light Processing projector with a monochrome event camera to produce RGB‑D data. By projecting structured light and capturing asynchronous brightness changes, the system can detect color and depth for each pixel, achieving a color detection speed of 1400 fps and a depth detection rate of 4 kHz. The approach enables frameless RGB‑D sensing and delivers colorful point clouds without compromising spatial resolution.
SimFuse3D tackles cross‑platform LiDAR unsupervised domain adaptation by addressing box‑point inconsistency through source‑guided target simulation and confidence‑guided multi‑stage localization reweighting. It preserves target placement, repairs pseudo‑objects using labeled source geometry, and reweights predictions based on confidence, all during adaptation without altering the detector architecture. The method outperforms existing adaptation techniques across six cross‑platform transfers and ranks first on nuScenes‑to‑KITTI for both evaluated detectors.
CrossDepth introduces geometry-constrained attention for multi-view surround depth estimation, addressing cross-image inconsistencies caused by varying camera intrinsics and limited receptive fields. The method conditions features on per-pixel camera-aware ray embeddings and extends pixel context via cross-image attention limited to geometrically plausible regions. Trained self-supervised with photometric consistency, it achieves better depth accuracy and consistency on DDAD and nuScenes compared to existing self-supervised approaches.
The study introduces an explainable OCTA pipeline for Alzheimer’s disease phenotyping that combines vessel segmentation, layer‑specific biomarker extraction, and label‑free phenotyping with large language model (LLM) reporting. Using 117 images from 39 subjects, the segmentation models achieved high ROC‑AUC (0.916–0.970) and Dice scores (0.695–0.781), and six vascular biomarkers were used to create subject‑level profiles for exploratory clustering. LLMs (GPT, Gemini, Llama) produced measurement‑grounded reports evaluated for citation faithfulness and diagnostic caution, offering a transparent, non‑diagnostic link between retinal vascular data and Alzheimer’s research.
MEOX is a compact multimodal masked autoencoder designed for Earth Observation that uses a 2.939 million‑parameter encoder and 3.115 million total parameters. It incorporates sensor‑specific adapters, explicit validity signals, and a shared sparse‑expert block to maintain modality‑dependent processing before a learned patch‑wise fusion, followed by fourteen encoder blocks that process a single spatial sequence with four metadata tokens. Pretrained on 1.228 million MMEarth64 samples, MEOX achieves strong performance on GEO‑Bench tasks, surpassing prior CSMoE results, and demonstrates effective sensor‑flexible representation learning with a modest parameter budget.
The paper surveys how commonsense reasoning is being integrated into computer vision, moving beyond traditional CNNs that only detect objects. It reviews methods that use knowledge graphs, scene graphs, neuro-symbolic models, and transformers to add contextual understanding, thereby improving object recognition and spatial reasoning. The authors also discuss current limitations such as dataset bias and knowledge gaps, and propose future research directions in cross‑modal reasoning, scalable knowledge injection, and hybrid architectures.
The paper presents the first scalable, end‑to‑end pipeline for automated detection of fossil palynomorphs in whole‑slide, multifocal digital microscopy images. It introduces efficient image decomposition and compression into 2‑D tiles, benchmarks modern object detection models (including RF‑DETR) achieving an AP@50 of 0.879, and provides algorithms for synthesizing detections across large‑scale images. The pipeline reduces analysis time from days of manual inspection to under one hour, enabling larger‑scale palynological studies.
The paper introduces FlexDepth, a family of self‑supervised monocular depth estimation models designed for robust driving perception. FlexDepth uses a two‑stage static‑dynamic decoupled training strategy and a Scale‑Driven Decoder that selects components based on scale size, enabling efficient feature fusion and high‑precision depth maps. Experiments on driving benchmarks show state‑of‑the‑art performance across arbitrary scales with minimal computational cost, with the smallest model (Flex‑Nano) achieving 37.6 FPS on mobile devices.
The paper introduces SAWRD-Net, a symmetry‑aware network for detecting water reflections. It uses dihedral group‑equivariant convolutions, a multi‑scale reflection equivariant block with symmetric attention, and a matrix‑decomposition decoder to regress keypoints on the reflection axis. On the largest water reflection dataset, SAWRD‑Net achieves a 0.890 true‑positive rate, surpassing existing detectors.
WeakMCN introduces a multi-task collaborative network that jointly learns weakly supervised referring expression comprehension (WREC) and segmentation (WRES) using a dual-branch architecture. The WREC branch employs anchor-based contrastive learning and serves as a teacher for the WRES branch, while two novel modules—Dynamic Visual Feature Enhancement (DVFE) and Collaborative Consistency Module (CCM)—facilitate cross-task collaboration. Experiments on RefCOCO, RefCOCO+, and RefCOCOg show significant performance gains over single-task baselines, with up to 3.91% and 13.11% improvements on WREC and WRES respectively, and strong generalization in semi-supervised settings.
The paper introduces an adaptive temporal modeling framework for weakly supervised video anomaly detection that addresses the limitations of rigid Multiple Instance Learning approaches. It presents a Temporal Refinement Module using dynamic positional encoding and a learnable class token to capture long‑range dependencies, and an Event Segmentation Module that identifies event boundaries via temporal discontinuity analysis to produce discriminative event‑level representations. An adaptive similarity‑based fusion strategy replaces fixed top‑k heuristics, dynamically integrating snippet‑level and event‑level anomaly scores into video‑level predictions, and the method outperforms state‑of‑the‑art baselines on two benchmarks.
SCAPES is a lightweight, resource‑efficient generative model that synthesizes high‑fidelity environmental sounds with high‑level semantic control. It operates on the continuous latent manifold of a neural audio codec, using a segmentation strategy and a Continuous Normalizing Flow to model latent trajectories. A 36‑million‑parameter instance can be trained on limited, uncurated data with a single consumer‑grade GPU, achieving convergence in roughly twice the source audio duration and enabling smooth semantic interpolation.
The paper introduces TSR-ITNR, a two‑stage, self‑supervised framework for hyperspectral image super‑resolution that fuses high‑resolution multispectral and low‑resolution hyperspectral data. Stage 1 refines an implicit Tucker representation using a low‑rank spatial tensor and spectral basis, enhanced by a pretrained denoiser, to capture fine spatial details and spectral correlations. Stage 2 applies parameter‑free calibration to extract complementary corrections from both observations, preserving geometry and ensuring orthogonal complementarity, leading to superior reconstruction quality demonstrated on benchmark datasets and improved downstream segmentation performance.
The paper introduces a confidence‑normalized continuous multi‑timescale representation for event cameras, using logarithmic B‑spline temporal encoding and a geometry‑aware local confidence mechanism. When paired with a fixed feed‑forward EventCenterNet detector, this representation outperforms the compact CSTR representation on the PEDRo and Gen1 datasets. Additionally, a recursive exponential‑polynomial approximation is proposed to allow efficient event‑by‑event updates while maintaining detection performance.
The paper argues that explainable AI for computer vision has focused too much on developing interpretability methods rather than assessing how interpretable the models themselves are. It proposes a shift toward model-centric evaluation, using existing tools to compare what different models represent and compute, and emphasizes the need to measure whether humans can truly understand these models. The authors review the current toolbox, survey limited model comparison work, draw parallels to systems neuroscience, and outline a future agenda for model-focused XAI.
The paper introduces LUMIN, a lightweight network for manufacturing anomaly detection, and PSP, a four‑stage adaptive memory bank sampling pipeline that eliminates backbone forward passes. PSP achieves near‑random construction speed, 341× faster than FPS, while parallel similarity computation and stratified pixel sampling cut inference time by 20× with minimal accuracy loss. Experiments on five benchmarks show that LUMIN and PSP reach state‑of‑the‑art sampling accuracy with dramatically reduced latency and memory usage.
CLON (Cue‑Calibrated Linguistic Object Onboarding) is a zero‑shot front‑end for 6D pose estimation that requires no task‑specific training for new objects. It builds a linguistic semantic memory from rendered templates to generate high‑recall proposals and computes fixed cue weights to calibrate proposal scoring. On seven BOP‑Classic‑Core datasets, CLON boosts detection AP by 8.1 pp, segmentation AP by 6.2 pp, and downstream 6D pose AR by up to 4.1 pp compared to existing front‑ends.
The paper introduces Dual-Part MLBNet, a multi-lateral branched network designed for fast, accurate, and explainable multi-class segmentation of cardiovascular catheterization angiograms. The architecture uses multi-lateral encoder blocks for diverse feature extraction and multi-head decoder branches that specialize in different structural properties, enabling simultaneous segmentation of guidewire, catheter, vessels, and background. Experiments on phantom, synthetic human-simulated aorta, and animal model angiograms demonstrate high overall accuracy and effective separation of foreground structures from background.
Weather-Conditioned Depth Anything (DA‑W) is a new framework that enhances monocular depth estimation models, like the Depth Anything series, to perform robustly under adverse weather conditions such as fog, rain, snow, and low‑light. It achieves this by disentangling style from content: a Style Filter extracts weather‑specific embeddings from a curated mix of real and synthetic degradation data, which are then injected into the backbone via a lightweight, zero‑initialized adapter. The adapter is trained with pseudo‑label distillation and alignment, enabling a single unified model to adapt to diverse weather scenarios while preserving its generalization on clean data, and it achieves state‑of‑the‑art performance with an average 3.7% improvement in AbsRel on weather benchmarks.