Computer Vision - Weekly Roundup

AdvScene, a conditional latent diffusion model that is trained in two stages that Conditioning on ego driving displacement prevents the ego from remaining static, and RL finetuning induces criticality directly with non-differentiable safety-critical metrics is proposed.

Findings indicate that Federated Learning is a safe and efficient solution to AI-assisted diagnosis in contemporary healthcare when combined with the use of sophisticated object detection models.

A hybrid approach that draws on the stability and generation quality of denoising diffusion models, which yields a stable training process and generates microstructures of varying complexity with minimal slice artefacts and close agreement with ground-truth phase fractions and structural descriptors.

PointEvent is proposed, a lightweight event-wise state-space framework that alternates serialized scans across the complementary orders, progressively consolidating fragmented motion evidence beyond fixed local neighborhoods, and achieves SOTA with the fewest parameters and fastest measured inference among the compared methods.

AdvScene, a conditional latent diffusion model that is trained in two stages that Conditioning on ego driving displacement prevents the ego from remaining static, and RL finetuning induces criticality directly with non-differentiable safety-critical metrics is proposed.

Findings indicate that Federated Learning is a safe and efficient solution to AI-assisted diagnosis in contemporary healthcare when combined with the use of sophisticated object detection models.

A hybrid approach that draws on the stability and generation quality of denoising diffusion models, which yields a stable training process and generates microstructures of varying complexity with minimal slice artefacts and close agreement with ground-truth phase fractions and structural descriptors.

PointEvent is proposed, a lightweight event-wise state-space framework that alternates serialized scans across the complementary orders, progressively consolidating fragmented motion evidence beyond fixed local neighborhoods, and achieves SOTA with the fewest parameters and fastest measured inference among the compared methods.

DART, a training-free method that combines low-rank coordinate transport with target-schedule response calibration with forward evaluations and no source training videos is proposed, and Adapter-level results reveal positive functional effects for some adapters and strong attenuation with reduced negative functional effects for others.

PACE (Precise AI Cinematic Expression), a typed representation for the plan: the screenplay evidence, the characters, props and locations it needs, where each subject stands, and what the camera does.

BinoGen is presented, an automated framework for generating large-scale, embodiment-aware egocentric binocular visual experiences in indoor environments and incorporating BinoGen data consistently improves real-world visual perception, including depth estimation, object detection, and video object tracking.

SeetaPsych v1.0 is presented, an open source, unified and extensible computer vision toolkit designed to extract psychologically relevant signals from facial images and/or face based videos to offer an integrated and accessible visual measurement platform for research in psychology, behavioral science, human computer interaction, and related fields.

A task-oriented framework that bypasses image reconstruction and directly transmits semantic features extracted by a multitask-pretrained backbone is investigated, with the largest improvements in the low-SNR regime.

NeuSOGA3D (Neuro-Symbolic Geometric Abstraction in 3D), a hybrid framework that combines learned perceptual priors inherited from NeuSOGA with explicit symbolic geometric reasoning for explainable geometric intelligence, is presented.

G^2RA-Net is proposed, a medical image segmentation framework that combines graph-based cross-slice relation modeling with atten- tion gating that outperforms representative methods in accuracy and boundary quality.

CrossUAV is introduced, a UAV benchmark for joint object detection and instance segmentation that provides a unified evaluation platform for cross-granularity task collaboration and Cross-Granularity Socialized Collaboration is proposed, a progressive and adaptive framework that regulates when, where, and how tasks exchange information across network hierarchies.

Graph-Guided Token Merging (G2TM) is extended, a single module inserted early in a ViT-based network, beyond its original Segmenter setting, and its behavior and accuracy-efficiency trade-off are consistent across every tested architecture for a given backbone size, indicating that its effectiveness is a property of the encoder rather than the decoder.

CapMap-MS-TTA is presented, a training-free submission built on Microsoft Florence-2-base, combining caption keyword mapping with multi-scale flip test-time augmentation, and ranks 3rd on the final MUMU leaderboard.

CamoShift is the first to target both visual stealthiness and attack success in visible-infrared object detection, and is the first to target both visual stealthiness and attack success in visible-infrared object detection.

ACT is the first framework to study semi-supervised VIOD under this image-pair-level setting and forms consensus pseudo labels under pair-preserving views to recover branch-wise misses and supervise unlabeled pairs.

Inspired by iterative error feedback in structured prediction, FAPR represents the current segmentation mask as a dynamic failure state and models each repair operation as a state-transition operator, enabling later operations to adapt to preceding changes.

A fully automatic multi-signal release frame detection (MS-RFD) method for hammer throw using reconstructed 3D hammer trajectories and shows that speed dynamics and radial expansion provide the strongest signals for release frame detection, while angular velocity and post-release linearity provide smaller refinements.

This work proposes a latency-aware metric for multi-object tracking called streaming-HOTA (s-HOTA), and introduces an ultra-High-resolution Airborne Remote-sensing Dataset (HARD) annotated at three levels for object detection, multi-object tracking, and scene-level visual question answering.

Efficient Unified Multimodal Understanding (EUMU), the winning solution for the MUMU Track of the 8th LSVOS Challenge, builds on a shared pretrained multimodal model, using its prompt-based capabilities for detection and captioning and training lightweight heads on shared visual features to predict quality, scene, and event tags.

The results suggest that shifting part of the modeling burden from network parameters to a structured input representation can support compact multi-task vision systems with reduced data, memory, and compute requirements.

METALICA, which implements Metadynamics on a pretrained diffusion model via Replica Exchange, is introduced, which implements Metadynamics on a pretrained diffusion model via Replica Exchange and accumulates a bias potential along a Collective Variable, repels new samples from previous ones through biased sampling, and reweights samples onto the unbiased distribution.

Overall, FedAvg provided the most consistently reliable server-based baseline, topology-aware gossip offered a viable decentralized alternative, and Hybrid Gossip-FedAvg provided a balanced compromise between peer-to-peer diffusion and periodic global coordination.

This paper establishes the first cross-domain RRSIS benchmark, designated as the Vaihingen-Potsdam Referring (VPRef) dataset, and develops a tailored parameter-efficient domain adaptation baseline anchored on the Segment Anything Model (SAM3) via Low-Rank Adaptation (LoRA).

This work proposes a one-pass conditional 3D rectified flow (3D Flow) framework for whole-body PET image denoising that incorporates a novel optimized non-uniform sampling strategy and shows promising zero-shot transfer performance across the evaluated datasets and unseen dose levels.

DE-GAN is proposed, a contrast-enhancing conditional GAN that combines input-adaptive dynamic convolutions, style-aware feature mixing, and coordinate encoding to synthesize slice-adaptive FLAIR images to synthesize slice-adaptive FLAIR images.

Qualitative and quantitative experiments demonstrate that FRPSS achieves the best Single Image Fr\'echet Inception Distance (SIFID) scores on all three datasets while maintaining competitive Learned Perceptual Image Patch Similarity (LPIPS).

QALPA ("Quantum-Aware Learning for Property-space Augmentation"), a property-guided generative framework that combines an E(3)-equivariant diffusion model with active learning and efficient quantum-mechanical methods to iteratively explore targeted QM property manifolds, is introduced.

This work finetune an image feature extractor for classifying attributes representing the downstream object classes, where the class attributes have been specified by experts under various encoding formats, and proposes an automatic selection of potential missclassified data.

GazeDiT is introduced, a diffusion model that generates images for a requested 4D gaze through an internally constructed spatial condition that grounds the global gaze label in this local geometry, and achieves substantially lower tail gaze-label error than other diffusion baselines.

It is suggested that uncertainty mapping for Fazekas score predictions can support model interpretation and targeted dataset review when reference labels are affected by ambiguity/ inter-rater variability.

Across six diverse visual reasoning tasks including multi-view spatial reasoning and collision prediction, ReImaGin consistently outperforms both text-only reasoning and specialist vision-tool baselines, with gains of up to 25\%, demonstrating the advantage of flexible, generative visual reasoning.

The wealth of information encoded in the Auger spectrum offers the opportunity to train convolutional neural networks for site-selective functional group classification in organic molecules directly from the Auger spectrum lineshape, demonstrating the potential for new data-driven characterization capabilities in spectroscopic techniques that are information-rich but difficult to interpret.