cs.CV · 2026-06-06 · No. 15
Computer Vision and Pattern Recognition, 2026-06-06.
10 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
10 entries-
01
A Vision-language Framework for Comparative Reasoning in Radiology
Tengfei Zhang, Ziheng Zhao, Lisong Dai, Xiaoman Zhang, Pengcheng Qiu, Ya Zhang, Yanfeng Wang, Weidi Xie
cs.CV · cs.IR · cs.LG · eess.IV
Medical imaging artificial intelligence has achieved strong performance in isolated image interpretation, but remains poorly aligned with radiological practice, where diagnosis and follow-up rely on comparison across prior studies and analogous reference cases. Here we formulate radiological comparison as an entity-aware cross-image reasoning problem and introduce a framework that supports both reference-case retrieval and temporal...
-
02
HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes
Wenbo Li, Xiaoliang Ju, Zipeng Qin, Rongyao Fang, Hongsheng Li
cs.CV · cs.AI
Indoor scene generation is crucial for robot simulation and modern interior design. However, complex layouts together with scarce 3D scene data make learning-based generation challenging. Existing methods often rely on hand-crafted rules or focus on isolated sub-tasks (e.g., floorplan synthesis or single-room furnishing), producing whole-home scenes that lack global coherence, realism, and simulation readiness. To mitigate these limitations,...
-
03
EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
Qiwei Zeng, Hao Wang, Jinghao Lin, Shuchang Ye, Yuezhe Yang, Yige Peng, Haoyuan Che, Jinman Kim, Lei Bi
cs.CV · cs.AI
Medical vision-language models (VLMs) have shown increasing potential for clinical image interpretation, including lesion detection and report generation. However, their practical utility remains limited by insufficient sensitivity to subtle lesions, whose visual evidence is often sparse, low-contrast, and embedded within complex anatomical context. As local visual tokens are aggregated, these weak lesion cues can become underrepresented in...
-
04
Towards One-to-Many Temporal Grounding
Qi Xu, Yue Tan, Shihao Chen, Jiahao Meng, Anna Wang, Shunping Ji, Hao Fei, Jason Li
cs.CV · cs.AI
Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, however, often require localizing multiple disjoint segments for a single query -- a setting we term One-to-Many Temporal Grounding (OMTG). Previous state-of-the-art MLLMs, optimized for one-to-one settings, struggle in this context, often yielding near-zero scores...
-
05
GRAMformer: Any-Order Modality Interactions via Volumetric Multimodal Cross-Attention
Giordano Cicchetti, Eleonora Grassucci, Danilo Comminiello
cs.CV · cs.LG
Transformer-based multimodal models rely on attention mechanisms to integrate information across heterogeneous modalities. Despite their success, existing multimodal attention formulations compute their scores through collections of pairwise dot-product interactions or by concatenating all the modalities into the keys, even when multiple modalities should be jointly involved. As a consequence, current approaches either incur quadratic...
-
06
Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology
Yanqing Luo, Julius Hense, Niklas Prenißl, Andreas Mock, Klaus-Robert Müller, Thomas Schnake, Mina Jamshidi Idaji
cs.CV · cs.LG
Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology. Existing methods primarily rely on heatmaps that highlight influential regions but do not explain how evidence from different tissue regions is combined to produce a prediction. This limits interpretability, especially when decisions depend on interactions between tissue features. We introduce Symbolic explainable...
-
07
DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments
Tan Zhang, Quanyou Li, Lu Zhang, Jun Liu, Xiaofeng Zhu, Ping Hu
cs.CV · cs.AI
When a disaster unfolds, responders must answer not only what is happening, but also why it is happening, what will happen next, and what to do now, often from noisy low-altitude UAV views and under tight on-site compute constraints. However, most existing multimodal benchmarks emphasize perception (e.g., recognition/description), cover limited disaster types, and provide insufficient support for the multi-stage reasoning required in...
-
08
ATT-CR: Adaptive Triangular Transformer for Cloud Removal
Yang Wu, Ye Deng, Pengna Li, Wenli Huang, Kangyi Wu, Xiaomeng Xin, Jinjun Wang
cs.CV · cs.AI
Cloud removal aims to accurately reconstruct the ground objects obscured by clouds in remote sensing images. Existing Transformer-based methods utilizing self-attention have shown impressive results by effectively modeling long-range dependencies in cloudy images. However, they suffer from the following issues: 1) the high computational complexity of self-attention limits scalability; 2) treating both cloudy and clean pixels as valid within...
-
09
Deep Learning-based 3D Oral Cavity Reconstruction Using 2D Intraoral Images
Jihun Cho, Soo-Yeon Jeong, Eun-Jeong Bae, Sun-Young Ihm
cs.CV · cs.AI
Oral 3D modelling is one of the most essential stages in dentistry, and many different approaches, such as impression taking and intraoral scanning, are commonly used for this phase, each with notable limitations. Impression taking, which involves placing alginate or silicone material in a tray and inserting it into the patient's oral cavity to form a negative mold, suffers from significant patient discomfort, material deformation errors, and...
-
10
Video-Rate Streaming Stylization on a Vision-Aware MLLM-Conditioned Edit Diffusion: Asymmetric Batched Inference on a Distilled UNet + MLLM Text Encoder
Yoshiyuki Ootani
cs.CV · cs.LG
Aggressive distillation of the diffusion U-Net inverts the per-frame bottleneck of real-time text-to-image pipelines: once the denoiser is a 4-step or 1-step distilled student, the text encoder becomes the critical path. This inversion is most acute in vision-aware edit diffusion, where the encoder is a multimodal large language model (MLLM). We study the case of a 0.39B distilled edit U-Net paired with a 2.13B MLLM text encoder (Qwen3-VL)...
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.