cs.CV · 2026-10-26 · No. 154
Computer Vision and Pattern Recognition, 2026-10-26.
23 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
23 entries-
01
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
Yuhan Liu, Lianhui Qin, Shenji Wan
cs.CV · cs.AI · cs.RO
Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding remains difficult. Visual generative models offer rich priors over plausible arrangements, yet their outputs require geometric reasoning to become physically valid 3D scenes. We introduce SceneBloom, an agentic framework that...
-
02
Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly Detection
Bernardo Perrone Ribeiro, Erkut Akdag, Egor Bondarev
cs.CV · cs.LG
Few-shot industrial anomaly detection requires modeling category-specific normality from only a handful of defect-free images. Common approaches tie inference to stored exemplars, impose rigid linear structure, or risk reproducing anomalous content. Flownomaly instead casts the problem as normal-counterpart recovery in frozen DINOv2 feature space. Given normal supports, a velocity field is learned through conditional flow matching over frozen...
-
03
Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models
Dianye Huang, Jiamei Guo, Yue Zhou, Mingde Li, Yi Xiong, Wei Wang, Nassir Navab, Zhongliang Jiang
cs.CV · cs.AI
Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that addresses the mismatch between continuous measurement targets and discrete token-based numerical prediction. Methods: This article presents HAD-VLM, a hybrid autoregressive-diffusion framework that combines autoregressive text generation with continuous measurement prediction within a shared backbone. Visual prompt tuning...
-
04
LoCA: Enabling Multi-Modality in Geospatial Location Encoders
Panagiotis Koromilas, Eleanna Vali, Diogenis Antonopoulos, Eleni Saka, Dimitris Christofis, Nikolaos Ioannis...
cs.CV · cs.LG
Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We prove that this construction is structurally limited: any Lipschitz location encoder produces an output of intrinsic dimension at most 2, regardless of architecture or bandwidth, which forces the contrastive loss to strictly exceed its asymptotic optimum. Empirically, joint training also...
-
05
SP-Guide: Enhancing Aerial Vision-Language Navigation with Spatial Priors
Haoxiang Tang, Dong Zhou, Shen Tan, Minxuan Jiang, Xitong Li
cs.CV · cs.AI
Aerial vision-language navigation (AVLN) requires a UAV to reach a language-described target from partial egocentric observations while reasoning over large outdoor scenes. Existing approaches typically fuse view-centered RGB observations and globally anchored history maps as generic visual embeddings, leaving cross-modal spatial alignment to be learned from sparse navigation supervision. We present SP-Guide, a transformer- based...
-
06
SemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric Correspondences
Roy Amoyal, Shira Ifergane, Oren Freifeld
cs.CV · cs.AI
We introduce SemGeo-Gen, an unsupervised method for generating approximate cross-instance semantic-geometric supervision from weakly aligned 3D object collections. Our goal is not to recover exact point-level correspondences, which are often ambiguous across different instances and would require expensive, impractical manual supervision at scale. Instead, we automatically produce approximate correspondences that are semantically meaningful,...
-
07
EditJev: System One Routing for Image Editing Models
Zhile Guan, Xu Jiang, Yule Duan, Gongbo Zhang, Shuyu Wang, Xiao Chen, Jian Zhang
cs.CV · cs.AI
Instruction-based image editing models exhibit pronounced sample-specific performance variation: different models can produce substantially different results for the same source image and editing instruction, and the best-performing model often varies across requests. These models also differ substantially in inference latency, making fixed-model deployment inefficient. We therefore study image editing model routing, which dynamically selects...
-
08
Efficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF)
Khaled Waleed Dawoud, Muhammad Haris Khan
cs.CV · cs.AI · cs.LG
Deploying Vision-Language Models for video anomaly detection confronts a fundamental constraint. Their semantic reasoning demands computational budgets incompatible with the scale of real-world video streams. We present Signal-Aware Adaptive Fusion (SAAF), a framework that achieves efficient zero-shot anomaly detection through three key innovations. First, we introduce a dual-signal adaptive sampler operating in semantic embedding space: a...
-
09
PathJev: Decision-Native Vision-Language Modelling for Histopathology
Cristian Tommasino, Antonio M. Rinaldi
cs.CV · cs.LG
Vision-language models used for decisions in histopathology rarely return calibrated probabilities over the candidates a user cares about. Decision-native models write a question and a candidate set chosen at run time into the input and return a normalised distribution from a small decision head in one forward pass. We build PathJev-P, a decision-native model for histopathology: MedGemma-1.5-4B with LoRA adapters and a decision head, trained...
-
10
AutoMIL: Automated Multiple Instance Learning for Whole-Slide Image Classification
Jonas Waibel, Frank Kramer, Dominik Müller
cs.CV · cs.AI
Developing multiple instance learning pipelines for the classification of whole-slide images involves many interdependent design decisions and expertise in both pathology and machine learning. We present AutoMIL, an open-source framework that applies principles from the field of automated machine learning to tackle this task by automating integral pipeline steps, such as preprocessing, training and evaluation. In a benchmark evaluation with...
-
11
PROVE: Probabilistic Visual Grounding via Patch-Level Evidence for Vision-Language Models
Mayank Nautiyal, Tianru Zhang, Li Ju, Ekta Vats, Prashant Singh
cs.CV · cs.LG
Visual grounding with vision-language models such as CLIP typically produces a single deterministic relevance map for an image-query pair, without indicating whether the localisation is reliable or whether the referent is present at all. We introduce \textbf{PROVE} (\textbf{Pro}babilistic \textbf{V}isual Grounding via Patch-Level \textbf{E}vidence), a post-hoc evidential adapter that maps frozen CLIP patch features to per-patch Beta...
-
12
Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images
Somraj Gautam, Gaurav Harit
cs.CV · cs.AI · cs.CL
Recent advances in Vision-Language Models (VLMs) have significantly improved Visual Question Answering (VQA) performance, yet their reasoning over structured content such as tables remains inconsistent, often plagued by spatial misalignment and logical hallucinations. Existing approaches for improving table VQA typically rely on architectural modifications or expensive supervised fine-tuning (SFT), which impose high barriers to entry due to...
-
13
PASTA: Prompt-Aware Annealed Diffusion Sampling
Ren Ajiki, Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser, Ko Watanabe, Riku Takahashi, Andreas Dengel, Jinjia Zhou
cs.CV · cs.AI · cs.LG
While Diffusion models produce high-quality images, real-world visual design requires intentionally preserving clean regions for headlines, logos, or UI elements. Existing layout-aware text-to-image methods struggle to strictly preserve reserved regions, often introducing unwanted content that complicates downstream editing. Existing approaches either manipulate attention to displace content or suppress conditioning via noise-level...
-
14
4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents
Yanhao Jia, Yi Zhu, Yiran Zhong, Weigao Sun, Feida Zhu, Pengkun Jiao, Sihan Yang, Ming Ma, Steven Hoi, Erik Cambria
cs.CV · cs.AI · cs.CL · cs.MM
Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicting long-horizon events. In contrast, existing benchmarks focus on short- and medium-context tasks, and most foundation models struggle to preserve fine-grained information over long horizons. To evaluate and improve long-horizon spatiotemporal reasoning, we introduce the...
-
15
GeoLEON-CLIP: Graph-Anchored Multimodal Contrastive Learning for Geographic Region Representation
Radoslaw Malek, Szymon Soltysiak, Aleksandra Kawala-Sterniuk, Piotr Szymanski
cs.CV · cs.LG
Geographic regions are multimodal: satellite imagery captures visual morphology, text conveys human-interpretable semantics, and map structures describe urban context. Existing geospatial contrastive methods typically align image-text or image-location pairs, underusing structured map data. We introduce GeoLEON-CLIP, a graph-anchored contrastive framework that aligns three views of each H3-indexed region: an OpenStreetMap-derived graph...
-
16
Complementing DINO Features with Image Structure for Part Discovery
Samyak Rawlekar, Nikhil Chowdary Paleti, Amey Gupta, Narendra Ahuja
cs.CV · cs.AI · cs.LG
Self-supervised Vision Transformers (ViTs) like DINO encode rich semantics, enabling training-free segmentation of objects from the background and discovery of their parts via feature clustering. This paper focuses on part discovery: partitioning a foreground object into semantic parts. Existing approaches produce imprecise part boundaries. We trace this to the rigid ViT patch grid used in training DINO, where patches straddling boundaries...
-
17
ReLEAP: Upcycling Vision Datasets through Cross-Task Unification and Semi-Supervised Annotation
Julia Simon, Daniel Steininger, Andreas Trondl
cs.CV · cs.LG
Developing robust vision models requires large amounts of annotated data, especially for tasks involving fine-grained class distinctions under variable environmental conditions. Even in domains with numerous existing datasets, differences in annotation formats, label definitions and targeted learning tasks hinder data reuse and integration. To address this challenge, we introduce ReLEAP, a scalable Python framework for unifying heterogeneous...
-
18
RootDown: Deploying and Benchmarking Models for Beet-Root Detection on Edge Devices
Gerardus Croonen, Andreas Trondl, Julia Simon, Daniel Steininger
cs.CV · cs.LG
Quality inspection of sugar beets after harvest and storage is critical to preserve sugar content and ensure optimal processing efficiency. The transfer of harvested beets to field clamps or trucks provides an opportunity to visually inspect individual beets automatically on loader conveyors. However, this is a challenging task as the large number of beets causes partial overlap and occlusion, complicating both annotation and detection. In...
-
19
Beyond Pattern Matching in 3D MLLMs: Part-Level Functional Reasoning for Generalizable Recognition
Weihong Li, Hao Jiang, Yaohua Zha, Tao Dai, Shu-Tao Xia
cs.CV · cs.AI
3D MLLMs recognize objects via pattern matching, which fails when geometrically similar objects require functional reasoning to disambiguate (e.g., dresser vs. wardrobe). Our per-sample Geometric Confusion Score (GCS) exposes this failure: baseline accuracy is 33.7% on ModelNet40's most ambiguous 20% versus 84.0% on its least ambiguous 20%. We identify a function-as-annotation pattern, in which functional language decorates a known identity...
-
20
Representation Learning via Composite Subspace Flow Matching
José Afonso, Mário Figueiredo
cs.CV · cs.AI
Distilling semantic meaning from raw image data remains a challenge in machine learning. Current self-supervised paradigms face a trade-off: joint-embedding architectures produce relevant features by aggressively discarding intra-class variance, irreversibly spatial and reconstruction. Conversely, generative models preserve spatial details but struggle to isolate semantics, as their optimization is dominated by pixel variations. To bridge...
-
21
Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction
Ziang Zhang, Wenyou Yi, Zehan Wang, Jiachen Xu, Xintong Han, Chunchao Guo, Zhou Zhao
cs.CV · cs.AI
Single-image 3D scene construction is a fundamental problem in 3D vision. Recent methods such as SAM-3Dfy enable end-to-end reconstruction of 3D assets and their scene layouts, but still struggle with fine-grained scene geometry and asset quality. Meanwhile, specialized 3D object generators provide detailed object geometry, while 3D foundation models offer strong and generalizable spatial understanding. We propose Easy-3Dfy, a compositional...
-
22
TileShare: Training-Free Acceleration of Overlapping Tiled ViT Decoding
Xiangzhong Ye, Zhongshen Li, Shen You, Ziyang Meng, Liang Xu, Junkai Ji, Qiuzhen Lin, Xiangtao Li, Ka-Chun Wong
cs.CV · cs.LG
Fixed-window Vision Transformer (ViT) decoders run at deployment resolution as overlapping tiles: every token in an overlap band is processed by several full decoder instances. In the 2.4B-parameter MiniMax-H3 video decoder, about half of all per-token computation is duplicated. Removing the tiles fails because attention, global tokens and coordinates are bound to them. TileShare keeps each released tile's attention and computes every other...
-
23
Neural Disjunctive Normal Forms for Learning Exact Rank Filters
Diego Marcondes, Wonder A. L. Alves, Ronaldo F. Hashimoto
cs.CV · cs.LG
Gradient-based learning of morphological operators is hindered by locally sparse derivatives with respect to the structuring elements. We develop a method for learning rank filters that retains exact operator evaluation while distributing the derivatives across the window. Using threshold decomposition, we construct a neural disjunctive normal form representation and establish a sufficient condition for exactness with integer-valued images...
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.