paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing

Junliang Ye, Kenkun Liu, Guocun Wang, Yang Li, Yansong Qu, Chunshi Wang, Jingwei Xu, Yunhan Yang, Zibo Zhao, Jiachen Xu, Jiaao Yu, Lifu Wang, Zhihao Liang, Xin Huang, Zhuo Chen, Chunchao Guo

Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate understanding, generation, and editing. However, unified 3D modeling remains constrained by scarce multimodal data, particularly the lack of large-scale and geometrically consistent editing data. To address this limitation, we propose Hunyuan3D-Buffalo 1.0, a unified framework supporting 3D understanding, text-to-3D generation, instruction-guided 3D editing, and text-grounded part generation within a single architecture. To enable scalable training, we construct an 87M-scale 3D multimodal corpus, comprising 25M understanding samples, 50M text-to-3D pairs, and 12M editing pairs generated using Nano3D-v2. Architecturally, the framework combines Hunyuan3D-VLM for semantic, structural, and spatial understanding with Hunyuan3D DiT for high-fidelity 3D synthesis. The VLM provides multimodal semantic conditions for generation, while editing and part generation additionally condition the diffusion process on the source object representation to preserve its overall structure and unedited regions. Extensive experiments show that Hunyuan3D-Buffalo 1.0 achieves state-of-the-art or leading performance on text-to-3D generation and 3D editing benchmarks, while exhibiting strong understanding and part-generation capabilities. Our analysis further shows that both generation and understanding improve editing, demonstrating the effectiveness of unified 3D multimodal training. Project Page: https://tencent-hunyuan.github.io/Hunyuan3D-Buffalo1.0/

arXiv

Generative Brownian Bridge Diffusion In Motion Space For Enhanced Myocardial Strain Analysis

Rishov Paul, Frederick H. Epstein, Miaomiao Zhang

Myocardial strain analysis of cardiac magnetic resonance (CMR) images provides an important tool for evaluating cardiac function. However, current techniques require either human-adjusted post-processing with suboptimal regional accuracy, or specialized acquisitions with limited availability. In this paper, we propose to leverage the power of generative models to synthesize high-quality motion-derived strain values from routinely acquired CMR sequences. Specifically, we develop a novel Brownian bridge diffusion model in motion space to learn the probabilistic mapping between standard CMR motion estimated from widely adopted registration methods and highly accurate motion provided by advanced strain imaging techniques. To promote the fidelity of anatomical structure in the generation process, our model is conditioned on the corresponding CMR images. We validate our method on large-scale multi-center CMR datasets including subjects of paired standard cine CMR and advanced strain imaging acquisitions. Experimental results demonstrate that our framework significantly improves the accuracy of motion prediction and strain analysis from standard CMRs compared to existing learning-based approaches. Our research represents a new paradigm for potentially developing cost-effective, clinically deployable AI tools for cardiac function assessment with enhanced strain accuracy in busy clinical workflows. Our code is publicly available at https://github.com/Rishov-MIA/Brownian-Bridge-strain-analysis.

arXiv

Hough-SIFT: Robust Image Registration for Linear Structures via Hough Space

Masaki Satoh

Image registration is essential in applications such as electronic image stabilization. Scale-Invariant Feature Transform (SIFT), a widely used local keypoint detector and descriptor, typically provides accurate registration; however, it often fails in scenes with strong linear structures (e.g., shutters), where local features become ambiguous. We propose Hough-SIFT, a robust registration method that performs SIFT descriptor matching in Hough space. In this domain, linear structures form distinctive peaks that restore descriptor discriminability. Experiments demonstrate that Hough-SIFT is robust in linear scenes where SIFT frequently fails, while maintaining accuracy comparable to SIFT in normal scenes.

arXiv

CRC-HGD: A Histopathological Image Dataset for Grading Colorectal Cancer

Elham Amjadi, Amin Bahreini, Sayed Mohammad Hasan Emami, Sayyed Mohammadreza Hakimian, Alireza Fahim, Hojjatollah Rahimi, Hamidreza Bolhasani

Colorectal cancer (CRC) is the third most common cancer worldwide and the second leading cause of cancer-related deaths globally, with approximately 1,926,425 new cases and 904,019 deaths reported in 2022. Accurate histologic grading plays a critical role in prognosis and treatment planning for colorectal adenocarcinoma. In recent years, artificial intelligence and its subcategories, including machine learning and deep learning, have been increasingly employed for automated cancer detection and classification. An appropriate and well-organized dataset is the essential first step to achieve this goal. This paper introduces CRC-HGD, a histopathological microscopy image dataset of 1,914 images obtained from 214 colorectal adenocarcinoma patients (Grade I: 106, Grade II: 75, Grade III: 33). The specimens are H&E-stained colorectal tissue sections acquired at the Poursina Hakim Research Center of Isfahan University of Medical Sciences, Iran, diagnosed between 2014 and 2019, and graded according to the World Health Organization (WHO) criteria into three grades: well-differentiated (Grade I), moderately differentiated (Grade II), and poorly differentiated (Grade III). For each specimen, four magnification levels are provided: 4x, 10x, 20x, and 40x. The dataset is accessible via Mendeley Data (https://doi.org/10.17632/yfp5sfj47m.4) and at http://databiox.com, where the latest version is also available. The distinctive feature of this dataset is the provision of labeled specimens across all three differentiation grades at multiple magnification levels, enabling comprehensive computational analysis of colorectal cancer grading.

arXiv

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers

Jianing Deng, Yuanzhe Li, Jialu Wang, Song Wang, Tianlong Chen, Huanrui Yang, Jingtong Hu

Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic complexity of cross-view global attention quickly becomes the dominant computational bottleneck. While recent efforts attempt to improve efficiency through compressed or sparse attention, they fail to fully exploit the inherent sparsity and dynamic behavior of global attention. In this work, we present a comprehensive analysis of global attention across multiple F3R transformers and reveal that attention patterns are highly heterogeneous, dynamic, and extremely sparse across layers and attention heads. Motivated by these findings, we propose SAF3R, a training-free dynamic sparse attention framework tailored to F3R transformers. SAF3R integrates tailored sparse attention mechanisms with offline head profiling and an efficient online adaptation strategy to match input-dependent attention behaviors. Extensive experiments demonstrate that SAF3R achieves high sparsity ratios while preserving camera pose estimation and 3D reconstruction quality, translating into substantial end-to-end speedup on F3R transformers compared to existing methods. Code is available at https://github.com/jndeng/SAF3R

arXiv

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift

Dipesh Tharu Mahato, Rachel Ren

Visual shifts can cause a vision-language-action policy to fail after initially plausible behavior. We ask whether OpenVLA's internal activations contain signals associated with the steps before failure. We freeze the policy, record one MLP activation per LIBERO-10 step, and fit two linear monitors. Occlusion reduces task success from $57\%$ to $17\%$. Within failed matched-reset trajectories, a layer-16 logistic probe attains AUROC $0.972$ and AUPRC $0.352$, whereas action disagreement attains AUROC $0.496$. Without refitting, the occlusion-trained probe reaches AUROC $0.689$ on failed camera-jitter episodes. In a calibration check, however, the same layer-16 monitor averages 3.32 warning onsets per clean episode. This contrast shows that strong retrospective discrimination does not imply operationally quiet warning behavior. Because fitting and evaluation share tasks, resets, and seed, these results establish retrospective separability rather than prediction on independent episodes.

arXiv

NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation

Cheng Wan, Yongsen Mao, Wenzheng Wu, Yuxuan Xie, Chucheng Xiang, Runze Wang, Xiang Zhang, Zhongyuan Liu, Rushi Dai, Yuan Liu

Recently, Large Language Models (LLMs) have emerged as promising layout agents for 3D scene generation. Existing layout agents still suffer from implausible layout generation because most of them convert 3D assets and 3D layouts into textual descriptions as inputs and outputs, which involves severe information loss due to the modality gap between texts and 3D assets and 3D layouts. We propose NaLA, a native 3D LLM layout Agent for high-quality 3D scene generation by placing 3D assets in the scene. For the inputs, NaLA encodes 3D scene boundaries and 3D assets directly into the LLM, preserving fine-grained geometry and enabling explicit reasoning over relationships like collisions, surface supporting, and containment. To accurately output the positions and orientations of assets, NaLA adopts a coarse-to-fine prediction mechanism that first predicts discrete poses in an autoregressive manner and then refines the discrete poses with a continuous regression. Trained on diverse layout datasets, NaLA attains strong geometric perception and layout coherence. Experiments demonstrate that NaLA outperforms prior layout agents in both generation quality and inference efficiency, with comprehensive ablation studies to verify each component's effectiveness.

arXiv

The Hidden Evolution of Disguised Visual Context inside the VLM

Wish Suharitdamrong, Tony Alex, Xiatian Zhu, Muhammad Awais, Sara Atito

Visual tokens enter Large Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interact with the language space depends entirely on the integration architecture. Whether by treating visual tokens as in-context prompts within the input sequence or injecting them directly into the LLM's intermediate layers. A controlled comparison and understanding of how these architectural choices affect visual information and its internal transformation to integrate with the LLM remains underexplored. We provide a fair comparison by evaluating in-context and layer-wise injection VLM integration paradigms under identical training conditions across single image, multi-image, and video benchmarks. In doing so, we uncover a hidden evolution where visual tokens enter the LLM as disguised visual context, raw representations lacking linguistic structure, but are progressively reshaped depending on the integration paradigm, each capturing fundamentally different frequency characteristics of the visual signal. We show that this evolution inside the LLM determines what visual features the VLM can utilize effectively, how visual representations align with the language space, and ultimately how each paradigm performs across different tasks. We further demonstrate that attention allocation alone is insufficient, and that performance is driven by the quality of visual representations at each layer.

arXiv

Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection

Atmika Bhardwaj, Silvia Vock, Nico Steckhan

Generated (or synthetic) image data is increasingly used to augment or replace real training datasets when target imagery is scarce, expensive, or biased. For hand detection, particularly in occupational safety settings, public datasets mostly contain bare hands. This under-represents the variation in hand appearance introduced by gloves, tattoos, jewelry, and other personal protective equipment, creating a distribution shift that safety-critical applications encounter at deployment. We test whether generative inpainting, editing only the hand region of a real photograph to introduce accessories, can close this shift gap and improve detection of real hands at deployment. On a paired dataset of real images and their synthetic counterparts, we evaluate YOLOv8n hand detectors across six experiments (A-F), four of which involve training (A, C, D, E) under three random seeds each, evaluate them on a real test set and on a real-gloves-only test split, and report the mean average precision (mAP) at two overlap thresholds (mAP@0.5 and mAP@0.5:0.95) along with paired statistical tests. A two-stage experiment: train on real U synthetic data, then fine-tune the resulting weights on real-only at a lower learning rate, directionally improves mAP@0.5 compared to the real-only baseline model on the standard real test set, and narrows the real-gloves out-of-distribution gap. Another three-stage experiment preserves box-tightness best, achieving the highest mAP@0.5:0.95 among experiments in the study. The synthetic-data utility for safety-critical hand detection depends on the training procedure, and simple multi-stage experiments extract substantial real-deployment benefit from inpainted accessory data.

arXiv

DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver

Yuqing Chen, Lin Liu, Haisu Wu, Xiaopeng Zhang, Yaowei Wang, Yujiu Yang, Qi Tian

Video object removal frequently struggles to eliminate target objects and their associated complex physical effects (e.g., smoke and light) in real-world scenes. We attribute this challenge to a fundamental semantic--pixel conflict, which manifests at two aspects: condition-level modality dissonance and optimization-level objective entanglement. In terms of conditioning, modality dissonance emerges from single-modality information incompleteness and cross-modal dominance imbalance. During optimization, two conflicting objectives---high-level semantic erasure and pixel-level background preservation---are inextricably entangled within a single model. To address these conflicts, we propose DualEraser, a novel framework for joint video object and effect removal. First, a Bipartite Text prompt and a Multi-Conditional Capability Elicitation (MCCE) mechanism explicitly inject effect semantics and further leverage multimodal priors to address the limitations of individual modalities. Second, a Learnable Deep CFG Fusion (LD-CFG) module adaptively balances the relative dominance between the text and mask conditions. Finally, we introduce a decoupled expert architecture comprising a Locator for semantic erasure and a Preserver for background pixel alignment to break the objective entanglement. Extensive experiments demonstrate that DualEraser achieves state-of-the-art quantitative performance on standard benchmarks (e.g., gains of 2.16 dB and 1.44 dB on ROSE and VOR-Eval, respectively), while enabling robust removal of complex effects in open-world videos. https://cyqii.github.io/DualEraser.github.io/

arXiv

A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline

Mohamed Ahmed Mohamed, Xiaowei Huang

Object detection in adverse weather is critical for the safety of autonomous vehicles; however, the scarcity of labelled, real-world foggy data remains a significant bottleneck. In this paper, we propose Clear2Fog (C2F), an end-to-end, physics-based pipeline that simulates fog for clear-weather datasets under a unified camera and LiDAR framework. C2F combines monocular depth estimation with a novel atmospheric light estimation method to improve the physical consistency of synthetic fog generation while reducing structural artefacts and chromatic biases observed in existing frameworks. Utilising a training set of 270,000 images from the Waymo Open Dataset, we conduct an extensive data efficiency study to investigate whether environmental diversity can reduce dataset scale requirements and improve model generalisation under varying fog conditions. Our findings reveal that models trained on mixed-density fog datasets at 75% scale achieve performance that is not statistically different from those trained on fixed-density datasets at 100% scale, reducing synthetic training data requirements by 25%. We observe that this efficiency trend is consistent across two representative detector architectures. Furthermore, we investigate the sim-to-real transfer by using C2F-generated data as a pre-training foundation before fine-tuning on real-world fog data. We demonstrate that, within the evaluated settings, a relative 10x increase in the default fine-tuning learning rate reduces the negative transfer caused by standard fine-tuning, resulting in an absolute increase of up to 0.0117 mAP beyond the real-only baseline. Overall, this work demonstrates the value of diverse synthetic fog as a pre-training tool for real-world adaptation.

arXiv

SIFT-VTON: Geometric Correspondence Supervision on Cross-Attention for Virtual Try-On

Kosuke Takemoto, Takafumi Koshinaka

Diffusion-based virtual try-on methods achieve photorealistic synthesis through cross-attention mechanisms that transfer garment features to target body regions. However, these approaches rely on implicit learning of spatial correspondences, struggling to preserve fine details such as text and illustrations. We propose a novel approach, which we call SIFT-VTON, that utilizes SIFT keypoint matching to provide explicit geometric guidance for diffusion-based virtual try-on. Our method applies domain-specific filtering to SIFT keypoint matches between garment and person images, then converts these correspondences into spatial probability distributions that supervise cross-attention layers during training. This explicit supervision guides the model to learn precise spatial alignment, concentrating attention on geometrically consistent garment regions. Experiments on the VITON-HD dataset demonstrate significant improvements on unpaired metrics while maintaining competitive paired reconstruction metrics. Qualitative comparisons show superior preservation of text clarity and pattern alignment. Attention visualizations confirm that our method produces sharply focused attention on relevant garment details. This work demonstrates that classical geometric correspondence methods can effectively enhance modern diffusion models for conditional synthesis tasks. The source code will be available at https://github.com/takesukeDS/SIFT-VTON.

arXiv

Subject-Aware Multi-Granularity Alignment for Zero-Shot EEG-to-Image Retrieval

Lin Jiang, Qingshan She, Jiale Xu, Haiqi Xu, Duanpo Wu, Zhenzhong Kuang

Decoding visual content from electroencephalography (EEG) is important for understanding neural visual representations and developing non-invasive brain-computer interfaces. Existing approaches mainly improve EEG representation learning and cross-modal alignment while treating pretrained visual representations as fixed supervision targets. However, pretrained vision models organize information hierarchically, with different depths encoding complementary structural and semantic information, and the visual granularity most compatible with EEG may vary across subjects. To address this issue, we propose Subject-Aware Multi-Granularity Alignment (SAMGA), which makes visual-target construction an explicit part of EEG-visual alignment. SAMGA constructs adaptive visual supervision from multiple intermediate representations and models EEG-compatible visual granularity through a global granularity prior with subject-dependent residual calibration, enabling subject-aware training and subject-agnostic inference. Based on the resulting adaptive target, a coarse-to-fine alignment strategy first organizes global cross-modal geometry and then refines instance-level retrieval discrimination. On THINGS-EEG, SAMGA improves Top-1 retrieval accuracy over the strongest competing method by 8.7 percentage points under intra-subject evaluation and 12.0 percentage points under leave-one-subject-out evaluation. These results support a broader view of neural-visual alignment, in which performance depends not only on how neural representations are mapped, but also on what visual representations define their supervision.

arXiv

ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling

Jianxuan Yang, Xinyue Guo, Zhi Cheng, Kai Wang, Lipan Zhang, Jinjie Hu, Qiang Ji, Yihua Cao, Yihao Meng, Zhaoyue Cui, Mengmei Liu, Meng Meng, Jian Luan

Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-grained controllability remains challenging. Existing methods suffer from weak textual controllability under visual-text conflict and imprecise stylistic control due to entangled temporal and timbre information in reference audio. Moreover, the lack of standardized benchmarks limits systematic evaluation. We propose ControlFoley, a unified multimodal V2A framework that enables precise control over video, text, and reference audio. We introduce a joint visual encoding paradigm that integrates CLIP with a spatio-temporal audio-visual encoder to improve alignment and textual controllability. We further propose temporal-timbre decoupling to suppress redundant temporal cues while preserving discriminative timbre features. In addition, we design a modality-robust training scheme with unified multimodal representation alignment (REPA) and random modality dropout. We also present VGGSound-TVC, a benchmark for evaluating textual controllability under varying degrees of visual-text conflict. Extensive experiments demonstrate state-of-the-art performance across multiple V2A tasks, including text-guided, text-controlled, and audio-controlled generation. ControlFoley achieves superior controllability under cross-modal conflict while maintaining strong synchronization and audio quality, and shows competitive or better performance compared to an industrial V2A system. Code, models, datasets, and demos are available at: https://github.com/xiaomi-research/controlfoley.

arXiv

Learning Class Difficulty via Dynamic Focal Attention for Histopathology Segmentation

Lakmali Nadeesha Kumari Rathukohe Mudiyanselage, Sen-Ching Samson Cheung

Frequency-based loss reweighting, the standard remedy for imbalanced histopathology segmentation, implicitly assumes that rare classes are difficult. Yet difficulty also arises from morphological variability, boundary ambiguity, and contextual similarity, all largely orthogonal to class frequency. We propose Dynamic Focal Attention (DFA), a simple, efficient mechanism that learns class-specific difficulty directly within the cross-attention of query-based mask decoders. DFA adds a learnable per-class bias to the attention logits, reweighting representations before prediction rather than gradients after it. Initialised from a centred log-frequency prior to prevent gradient starvation and then optimised end-to-end, the bias adapts to difficulty signals as they emerge during training, unifying frequency- and difficulty-aware reweighting in a single attention-bias framework. On three benchmarks (BCSS, BDSA, CRAG), DFA consistently improves Dice and IoU, matching or exceeding a two-stage difficulty-aware baseline without a separate estimator or extra training stage. This shows that encoding difficulty at the representation level is a principled alternative to conventional loss reweighting.

arXiv

SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy

Peiyan Li, Yixiang Chen, Yuan Xu, Jiabing Yang, Xiangnan Wu, Jun Guo, Nan Sun, Long Qian, Xinghang Li, Xin Xiao, Jing Liu, Nianfeng Liu, Tao Kong, Yan Huang, Liang Wang, Tieniu Tan

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies neglect one or both aspects. They often rely on 2D visual observations or backbones pretrained on static image--text pairs, which leads to high data requirements and limited comprehension of environment dynamics. To address this, we introduce SpatialVAM, the first 3D Video Action Model that simultaneously predict spatial-aware multi-view heatmap videos and RGB videos. Our key insight is that this design naturally injects 3D information into video foundation models while aligning the representation format between video pretraining and action finetuning. Extensive experiments demonstrate that SpatialVAM enables data-efficient, robust, generalizable, and interpretable manipulation. With only ten demonstration trajectories and no additional pretraining, SpatialVAM handles challenging long-horizon and contact-rich tasks, generalizes to out-of-distribution settings, and predicts realistic future videos. Evaluations on Meta-World (22\%$\uparrow$), RoboCasa (15\%$\uparrow$) and real-world robotic platforms (16\%$\uparrow$) show that SpatialVAM consistently outperforms other video action models, vision language action models and 3D-based policies, establishing a new state-of-the-art in data-efficient multi-task manipulation.

arXiv

SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis

Bingxuan Zhao, Qing Zhou, Chuang Yang, Junyu Gao, Qi Wang

Text-to-image synthesis for remote sensing (RS) lacks an accessible, high-performance generative foundation, as directly training diffusion models at large, high resolutions is computationally prohibitive. Training-free resolution promotion via Rotary Position Embedding (RoPE) extrapolation offers an efficient alternative, but existing algorithms apply static scaling rules tailored to natural scenes, whereas RS imagery is dominated by dense, minute instances that hinge on high-frequency structural integrity. We present a comprehensive framework for large-scale RS synthesis. First, we curate over 100{,}000 image-text pairs to train RS-FLUX, a domain-specialized generative prior. Second, we propose \textbf{SHARP}, a training-free extrapolation algorithm that introduces a Rational Decay Scheduler to modulate RoPE frequencies throughout denoising: strong positional extrapolation early on enforces coherent global layouts, and progressive relaxation later recovers dense high-frequency details. Extensive experiments show that SHARP consistently achieves state-of-the-art performance across multiple promoted resolutions with negligible ($<$4\%) overhead, offering an efficient and structurally faithful solution for large-scale RS generation.

arXiv

OTPL-VIO: Robust Visual-Inertial Odometry with Optimal Transport Line Association and Adaptive Uncertainty

Zikun Chen, Wentao Zhao, Yihe Niu, Tianchen Deng, Jingchuan Wang

Robust stereo visual-inertial odometry (VIO) remains challenging in low-texture scenes and under abrupt illumination changes, where point features become sparse and unstable, leading to ambiguous association and under-constrained estimation. Line structures offer complementary geometric cues, yet many efficient point-line systems still rely on point-guided line association, which can break down when point support is weak and may lead to biased constraints. We present a stereo point-line VIO system in which line segments are equipped with dedicated deep descriptors and matched using an entropy-regularized optimal transport formulation, which performs global mass-transport assignment and supports unmatched observations under ambiguity, outliers, and partial observations. The proposed descriptor is training-free and is computed by sampling and pooling network feature maps. To improve estimation stability, we analyze the impact of line measurement noise and introduce reliability-adaptive weighting to regulate the influence of line constraints during optimization. Experiments on EuRoC and UMA-VI, together with real-world deployments in low-texture and illumination-challenging environments, demonstrate improved accuracy and robustness over representative baselines while maintaining real-time performance.

arXiv

Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning

Haoyi Jiang, Liu Liu, Xinjie wang, Yonghao He, Wei Sui, Zhizhong Su, Wenyu Liu, Xinggang Wang

Vision-language models excel at 2D visual understanding but remain limited in 3D spatial reasoning. Existing approaches either depend on explicit 3D modalities, which limits scalability, or inject partial, view-conditioned geometric priors and leave the language model to recover global scene structure from sparse cues. We introduce Spa3R, a self-supervised framework that learns a unified, view-invariant spatial representation from unposed multi-view RGB images. Its Predictive Spatial Field Modeling objective compresses context views into a compact latent representation and predicts aligned geometric and semantic feature fields at novel viewpoints, thereby encouraging coherent encoding of scene geometry and layout. We integrate the pre-trained Spa3R Encoder into a vision-language model through a lightweight residual cross-attention adapter, yielding Spa3-VLM and grounding language reasoning in global spatial context. Spa3-VLM achieves an average score of 58.6% on VSI-Bench and delivers leading or competitive performance across three additional spatial reasoning benchmarks. These results demonstrate that predictive spatial representation learning provides an effective visual foundation for 3D reasoning.

arXiv

SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models

Turhan Can Kargin, Wojciech Jasiński, Adam Pardyl, Bartosz Zieliński, Marcin Przewięźlikowski

Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities, which limits their applicability to embodied systems. As a result, recent work incorporates some 3D tasks (such as depth estimation) into VFM training. However, VFM performance remains inconsistent across other spatial tasks, raising the question of whether these models truly have spatial awareness or overfit to specific 3D objectives. To address this question, we introduce the Spatial Relation Recognition Task (SpaRRTa) benchmark, which evaluates the ability of VFMs to identify relative positions of objects in the image. Unlike traditional 3D objectives that focus on precise metric prediction (e.g., surface normal estimation), SpaRRTa probes a fundamental capability underpinning more advanced forms of human-like spatial understanding. SpaRRTa generates an arbitrary number of photorealistic images with diverse scenes and fully controllable object arrangements, along with freely accessible spatial annotations. Evaluating a range of state-of-the-art VFMs, we reveal significant disparities between their spatial reasoning abilities. Through our analysis, we provide insights into the mechanisms that support or hinder spatial awareness in modern VFMs. We hope that SpaRRTa will serve as a useful tool for guiding the development of future spatially aware visual models.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.