论文检索

Zirui Xu, Biao Yang, Rongrong Ni, Zhongkai Zhou, Shaobo Shen

Pedestrian trajectory prediction is crucial for applications such as autonomous driving and social robots. Recently, language model (LM)-based trajectory prediction has offered both prediction accuracy and interpretability. However, the L2 loss commonly used in trajectory prediction cannot be directly applied to LM optimization, resulting in degraded prediction performance. Moreover, current LM-based trajectory prediction methods lack explicit expressions of social interactions, and their scene descriptions are overly simplistic, making it challenging to impose practical scene constraints. To address these issues, we propose Write-to-Walk (W2W). First, we convert observed trajectories and interaction cues (companion/following/obstacle) into parsable textual prompts, so that interaction semantics are expressed more explicitly in the model input. Afterward, a T5-Small backbone is trained in a two-stage manner: (1) Full-parameter supervised fine-tuning with cross-entropy loss for language learning, enabling formatted question answering; (2) Reinforcement Learning (RL) to optimize W2W, where a reward function combining ADE error and off-road penalties strengthens scene constraints, producing future trajectories consistent with the scene context and further improving prediction accuracy. Experiments on benchmark datasets (ETH/UCY and SDD) demonstrate that W2W remains competitive with recent LM-based prediction methods and strong trajectory prediction baselines on ADE/FDE. The interpretability of LMs further supports W2W's deployment in safety-critical domains such as autonomous driving.

Xingguang Zhong, Liren Jin, Marija Popovic, Jens Behley, Cyrill Stachniss

Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, online SLAM is particularly challenging in dynamic natural environments, where scene dynamics can severely deteriorate camera pose estimation accuracy. In this work, we propose a novel monocular visual SLAM system that can robustly estimate camera poses in dynamic scenes. We leverage the complementary strengths of geometric patch-based online bundle adjustment and recent feed-forward reconstruction models. Specifically, we propose a feed-forward reconstruction model to precisely filter out dynamic regions, while also utilizing its depth prediction to enhance the robustness of the patch-based visual SLAM. By aligning depth prediction with estimated patches from bundle adjustment, we handle the inherent scale ambiguities of the batch-wise application of the feed-forward reconstruction model. Extensive experiments on multiple tasks show the superior performance of our proposed method compared to state-of-the-art approaches.

Xingkui Zhu, Dingkang Liang, Cheng Chen, Daoxin Zhang, lv Hanxiang, Zhe Xu, Yao Hu, Xiang Bai

Sparse activation layers, primarily Mixture-of-Experts (MoE) and memory-based modules, have become a central approach for scaling large models and are gaining traction in vision tasks. Despite conceptual similarities, these paradigms have evolved independently, hindering systematic comparison and the development of modules that exploit their complementary strengths. To bridge this gap, we propose OneSparse, a unified framework that reformulates MoE and memory modules under a common abstraction. This enables their systematic comparison and integration, revealing a continuous design space. Guided by this abstraction, we design the Nexus Layer, which features two key innovations: a unified routing mechanism that combines the efficiency of memory retrieval with MoE's load balancing to ensure stable and scalable token assignment, and an adaptive processing strategy where memory modules sketch coarse representations while expert modules refine critical regions. Extensive experiments on image classification, object detection, and semantic segmentation demonstrate that our Nexus Layer establishes a new performance--efficiency frontier, surpassing representative sparse baselines across convolutional and Transformer architectures. These results validate the power of the OneSparse framework to unify and integrate complementary sparse paradigms and underscore the potential of hybrid sparse modeling in vision.

Charantej Pochimireddy, Subhasmita Sahoo, Apoorva Verma, Palavalli Shyam, Swapnil Malviya, Sarvesh Sarvesh, Raj Gadde

Recent advancements in deep neural networks (DNNs) have significantly improved visual quality of camera captures under low-light (<10lx) conditions, yet visual quality in extreme low-light (<1lx) remains inadequate. Existing DNN models are computationally intensive and suffer from large processing times, making them impractical for real-time enhancement of high-resolution video. Consequently, Ultra HD (UHD) videos (4K/8K) captured in extreme low-light environments exhibit elevated noise and diminished detail. Developing DNN-based solutions for UHD video enhancement faces challenges including paired dataset creation, temporal consistency, and efficient deployment under strict latency (<33ms) and power constraints (<250mA for 30fps video).We present a comprehensive methodology for developing a real-time raw to raw denoising solution for UHD video in extreme low-light, designed for seamless integration into existing ISP pipelines. Unlike ISP-replacement approaches, our solution enhances commercial camera stacks across sensor platforms. Our framework comprises: (1) Diverse dataset creation methodology; (2) A low-complexity model architecture optimized for mobile compute elements; (3) Efficient training and post-training optimizations (reparameterization, restructuring, quantization) to meet latency constraints while ensuring high-quality output. The result is a power-efficient real-time raw to raw video denoiser that improves extreme low-light video quality while preserving downstream ISP behavior.

Fangtai Wu, Mushui Liu, Weijie He, Zhao Wang, Yunlong Yu

The unified autoregressive (AR) model excels at multimodal understanding and generation. However, its full potential in the domain of customized image generation has yet to be fully realized.Existing customization approaches for unified AR models face a fundamental dilemma: adaptation-based methods suffer from overfitting and scalability bottlenecks, while concept-injection paradigms are constrained by a shallow injection strategy that leads to poor visual fidelity and impaired re-contextualization.To address this, we propose DCoAR, a novel deep concept injection framework that maintains a completely frozen pre-trained model. DCoAR deeply integrates new concepts through a Layer-wise Multimodal Context Learning (LMCL) strategy, which is stabilized by a multi-faceted regularization scheme: a Dual Prior Preservation (DPP) loss to mitigate semantic drift and a Context-Aware Self-Regularization (CASR) loss to enhance re-contextualization. The framework also enables training-free subject customization in user-provided styles.Experiments demonstrate that DCoAR significantly outperforms previous injection-based methods and achieves performance competitive with adaptation-based approaches while requiring substantially fewer trainable parameters.

Huakeng Ding, Yaowen Chen, Kun Zhou, Hongzhi Wu

We present a differentiable framework to adaptively compute 4D illumination conditions with respect to an object, for efficient, high-quality simultaneous acquisition of its shape and reflectance, with a unified spatial-angular structured light and a single camera. Using a simple histogram-based pixel-level probability model for depth and reflectance, we differentiably link the next illumination condition(s) with a loss that encourages the reduction in depth uncertainty. As new structured illumination is cast, corresponding image measurements are used to update the uncertainty at each pixel. Finally, a fine-tuning-based approach reconstructs the depth map and reflectance parameter maps, by minimizing the differences between all physical measurements and their simulated counterparts. The effectiveness of our framework is demonstrated on physical objects with wide variations in shape and appearance. Our depth results compare favorably with state-of-the-art techniques, while our reflectance results are comparable when validated against photographs.

Chenye Wang, Qingyuan Cai, Saihui Hou, Aoqi Li, Yongzhen Huang

Gait recognition has emerged as a powerful biometric technique for identifying individuals at a distance without requiring user cooperation. Most existing methods focus primarily on RGB-derived modalities, which fall short in real-world scenarios requiring multi-modal collaboration and cross-modal retrieval. To overcome these challenges, we present MMGait, a comprehensive multi-modal gait benchmark integrating data from five heterogeneous sensors, including an RGB camera, a depth camera, an infrared camera, a LiDAR scanner, and a 4D Radar system. MMGait contains twelve modalities and 334,060 sequences from 725 subjects, enabling systematic exploration across geometric, photometric, and motion domains. Based on MMGait, we conduct extensive evaluations on single-modal, cross-modal, and multi-modal paradigms to analyze modality robustness and complementarity. Furthermore, we introduce a new task, Omni Multi-Modal Gait Recognition, which aims to unify the above three gait recognition paradigms within a single model. We also propose a simple yet powerful baseline, OmniGait, which learns a shared embedding space across diverse modalities and achieves promising recognition performance. The MMGait benchmark, codebase, and pretrained checkpoints are publicly available at https://github.com/BNU-IVC/MMGait.

Kaichen Zhang, Keming Wu, Zuhao Yang, Bo Li, Kairui Hu, Bin Wang, Xingxuan Li, Lidong Bing

Recent advancements in reasoning language models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual and video reasoning, the lack of transparent and reproducible data curation and training pipelines remains a major barrier to scalable research. In this work, we introduce OpenMMReasoner, a fully transparent two-stage recipe for multimodal reasoning spanning supervised fine-tuning (SFT) and reinforcement learning (RL). In the SFT stage, we construct an 874k-sample cold-start dataset with rigorous step-by-step validation, providing a strong foundation for reasoning capabilities. The subsequent RL stage leverages a 74k-sample dataset across diverse domains to further sharpen and stabilize these abilities, resulting in a more robust and efficient learning process. Extensive evaluations demonstrate that our training recipe not only surpasses strong baselines but also highlights the critical role of data quality and training design in shaping multimodal reasoning performance. Notably, our method achieves a 9.5% improvement over the Qwen2.5-VL-7B-Instruct baseline across nine multimodal reasoning benchmarks, establishing a solid empirical foundation for future large-scale multimodal reasoning research.

Chenrui Ma, Xi Xiao, Tianyang Wang, Xiao Wang, Yanning Shen

Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent interpolant intersections or introducing consistency and mean-velocity modeling to promote straight trajectory learning. However, these approaches often suffer from discrete approximation errors, training instability, and convergence difficulties. To tackle these issues, in the present work, we propose Straight Variational Flow Matching (S-VFM), which integrates a variational latent code representing the "generation overview" into the Flow Matching framework. S-VFM explicitly enforces trajectory straightness, ideally producing linear generation paths. The proposed method achieves competitive performance across three challenge benchmarks and demonstrates advantages in both training and inference efficiency compared with existing methods.

Jiawei Zhang, Lei Chu, Jiahao Li, Zhenyu Zang, Chong Li, Xiao Li, Xun Cao, Hao Zhu, Yan Lu

We present a unified framework for reconstructing animatable 3D human avatars from a single portrait across head, half-body, and full-body inputs. Our method tackles three bottlenecks: pose- and framing-sensitive feature representations, limited scalable data, and unreliable proxy-mesh estimation. We introduce a Dual-UV representation that maps image features to a canonical UV space via Core-UV and Shell-UV branches, eliminating pose- and framing-induced token shifts. We also build a factorized synthetic data manifold combining 2D generative diversity with geometry-consistent 3D renderings, supported by a training scheme that improves realism and identity consistency. A robust proxy-mesh tracker maintains stability under partial visibility. Together, these components enable strong in-the-wild generalization. Trained only on half-body synthetic data, our model achieves state-of-the-art head and upper-body reconstruction and competitive full-body results. Extensive experiments and analyses further validate the effectiveness of our approach.

Zhuoqian Yang, Mathieu Salzmann, Sabine Süsstrunk

In this work, we investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruction, generation, and analysis tasks on 2D and 3D data, we find that multiplicative LoRA weights achieve high representation quality while exhibiting distinctiveness and semantic structure. When used with latent diffusion models, multiplicative LoRA weights enable higher-quality generation than existing weight-space methods.

Mukhiddin Toshpulatov, Wookey Lee, Suan Lee, Geehyuk Lee

Precise fingertip contact detection is a fundamental challenge for natural and immersive virtual reality (VR) interaction. However, existing vision-based methods suffer from insufficient accuracy, with typical depth errors (12-25 mm) being too large to reliably distinguish between hovering and true contact (<3 mm). While commercial motion capture systems provide sub-millimeter accuracy, their prohibitive cost limits widespread adoption. This paper addresses this critical gap by developing a highly accurate and cost-effective system for fingertip contact detection. We introduce a novel, specialised dataset of 53,300 RGB-depth pairs capturing millimeter-scale, hand-table typing interactions. By systematically fine-tuning six state-of-the-art depth estimation architectures on this dataset, we reduce the mean absolute error (MAE) by 68%, from 12.3 mm to a state-of-the-art 3.8 mm. Our complete VR keyboard system, TapBoard-X, achieves 95.96% contact detection accuracy and enables typing speeds of 45.6 WPM with a low 3.1% character error rate, rivalling physical keyboards. This performance is achieved at over a 90% cost reduction compared to commercial systems, democratising high-precision hand tracking for the broader research community and paving the way for the next generation of tactile VR experiences.

Vanessa Emanuela Guarino, Claudia Winklmayr, Jannik Franzen, Josef Lorenz Rumberger, Manuel Pfeuffer, Sonja Greven, Klaus Maier-Hein, Dagmar Kainmueller, Christoph Karg, Carsten T. Lüth

Uncertainty Quantification (UQ) is crucial for ensuring the reliability of automated image segmentations in safety-critical domains like biomedical image analysis or autonomous driving. In segmentation, UQ generates pixel-wise uncertainty scores that must be aggregated into image-level scores for downstream tasks like Out-of-Distribution (OoD) or failure detection. Despite routine use of aggregation strategies, their properties and impact on downstream task performance have not yet been comprehensively studied. Global Average is the default choice, yet it does not account for spatial and structural features of segmentation uncertainty. Alternatives like patch-, class- and threshold-based strategies exist, but lack systematic comparison, leading to inconsistent reporting and unclear best practices. We address this gap by (1) formally analyzing properties, limitations, and pitfalls of common strategies; (2) proposing novel strategies that incorporate spatial uncertainty structure and (3) benchmarking their performance on OoD and failure detection across ten datasets that vary in image geometry and structure. We find that aggregators leveraging spatial structure yield stronger performance in both downstream tasks studied. However, the performance of individual aggregators depends heavily on dataset characteristics, so we (4) propose a meta-aggregator that integrates multiple aggregators and performs robustly across datasets.

Sriram Narayanan, Ziyu Jiang, Srinivasa Narasimhan, Manmohan Chandraker

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation. Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback. This combination enables a generative model to produce physically consistent and controllable outputs through variations in physical attributes--without any simulator or geometry reconstruction at inference. On the Physics-IQ benchmark, PhyCo significantly improves physical realism over strong baselines, and human studies confirm clearer and more faithful control over physical attributes. Our results demonstrate a scalable path toward physically consistent, controllable generative video models that generalize beyond synthetic training environments.

Thanh-Dat Truong, Huu-Thien Tran, Jackson Cothren, Bhiksha Raj, Khoa Luu

Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can lead to biased model updates and suboptimal performance across tasks. While recent continual learning studies have made progress in addressing catastrophic forgetting, the problem of fairness caused by imbalanced data remains largely underexplored. This paper presents a novel Fairness Direct Preference Optimization (FaiDPO or \phi-DPO) framework for continual learning in LMMs. In particular, we first propose a new continual learning paradigm based on Direct Preference Optimization (DPO) to mitigate catastrophic forgetting by aligning learning with pairwise preference signals. Then, we identify the limitations of conventional DPO in imbalanced data and present a new \phi-DPO loss that explicitly addresses distributional biases. We provide a comprehensive theoretical analysis demonstrating that our approach addresses both forgetting and data imbalance. Additionally, to enable \phi-DPO-based continual learning, we construct pairwise preference annotations for existing benchmarks in the context of continual learning. Extensive experiments and ablation studies show the proposed \phi-DPO achieves State-of-the-Art performance across multiple benchmarks, outperforming prior continual learning methods of LMMs.

Haoran Zhou, Gim Hee Lee

Realistic reconstruction of dynamic 4D scenes from monocular videos is essential for understanding the physical world. Despite recent progress in neural rendering, existing methods often struggle to recover accurate 3D geometry and temporally consistent motion in complex environments. To address these challenges, we propose MotionScale, a 4D Gaussian Splatting framework that scales efficiently to large scenes and extended sequences while maintaining high-fidelity structural and motion coherence. At the core of our approach is a scalable motion field parameterized by cluster-centric basis transformations that adaptively expand to capture diverse and evolving motion patterns. To ensure robust reconstruction over long durations, we introduce a progressive optimization strategy comprising two decoupled propagation stages: 1) A background extension stage that adapts to newly visible regions, refines camera poses, and explicitly models transient shadows; 2) A foreground propagation stage that enforces motion consistency through a specialized three-stage refinement process. Extensive experiments on challenging real-world benchmarks demonstrate that MotionScale significantly outperforms state-of-the-art methods in both reconstruction quality and temporal stability. Project page: https://hrzhou2.github.io/motion-scale-web/.

Jihwan Park, Chanhyeong Yang, Jinyoung Park, Taehoon Song, Hyunwoo J. Kim

Weakly-supervised Human-Object Interaction (HOI) detection is essential for scalable scene understanding, as it learns interactions from only image-level annotations. Due to the lack of localization signals, prior works typically rely on an external object detector to generate candidate pairs and then infer their interactions through pairwise reasoning. However, this framework often struggles to scale due to the substantial computational cost incurred by enumerating numerous instance pairs. In addition, it suffers from false positives arising from non-interactive combinations, which hinder accurate instance-level HOI reasoning. To address these issues, we introduce Relational Grounding Transformer (RegFormer), a versatile interaction recognition module for efficient and accurate HOI reasoning. Under image-level supervision, RegFormer leverages spatially grounded signals as guidance for the reasoning process and promotes locality-aware interaction learning. By learning localized interaction cues, our module distinguishes humans, objects, and their interactions, enabling direct transfer from image-level interaction reasoning to precise and efficient instance-level reasoning without additional training. Our extensive experiments and analyses demonstrate that RegFormer effectively learns spatial cues for instance-level interaction reasoning, operates with high efficiency, and even achieves performance comparable to fully supervised models. Our code is available at https://github.com/mlvlab/RegFormer.

Chenghao Gu, Haolan Kang, Junchao Lin, Jinghe Wang, Duo Wu, Shuzhao Xie, Fanding Huang, Junchen Ge, Ziyang Gong, Letian Li 等

The rise of generalist robotic policies has created an exponential demand for large-scale training data. However, on-robot data collection is labor-intensive and often limited to specific environments. In contrast, open-world images capture a vast diversity of real-world scenes that naturally align with robotic manipulation tasks, offering a promising avenue for low-cost, large-scale robot data acquisition. Despite this potential, the lack of associated robot actions hinders the practical use of open-world images for robot learning, leaving this rich visual resource largely unexploited. To bridge this gap, we propose IGen, a framework that scalably generates realistic visual observations and executable actions from open-world images. IGen first converts unstructured 2D pixels into structured 3D scene representations suitable for scene understanding and manipulation. It then leverages the reasoning capabilities of vision-language models to transform scene-specific task instructions into high-level plans and generate low-level actions as SE(3) end-effector pose sequences. From these poses, it synthesizes dynamic scene evolution and renders temporally coherent visual observations. Experiments validate the high quality of visuomotor data generated by IGen, and show that policies trained solely on IGen-synthesized data achieve performance comparable to those trained on real-world data. This highlights the potential of IGen to support scalable data generation from open-world images for generalist robotic policy training. Code for IGen will be made publicly available.

Yufeng Zhong, Lei Chen, Zhixiong Zeng, Xuanle Zhao, Deyang Jiang, Liming Zheng, Jing Huang, Haibo Qiu, Peng Shi, Siqi Yang 等

Reading text from images or scanned documents via OCR models has been a longstanding focus of researchers. Intuitively, text reading is perceived as a straightforward perceptual task, and existing work primarily focuses on constructing enriched data engineering to enhance SFT capabilities. In this work, we observe that even advanced OCR models exhibit significantly higher entropy in formatted text (e.g., formula, table) compared to plain text, often by an order of magnitude. These statistical patterns reveal that advanced OCR models struggle with high output uncertainty when dealing with format sensitive document, suggesting that reasoning over diverse reading pathways may improve OCR performance. To address this, we propose Format Decoupled Reinforcement Learning (FD-RL) , which leverages high-entropy patterns for targeted optimization. Our approach employs entropy-based data filtration strategy to identify format-intensive instances, and adopt format decoupled rewards tailored to different format types, enabling format-level validation rather than token-level memorization. FD-RL achieves an average score of 90.41 on OmniDocBench, demonstrating highly competitive performance among end-to-end models on this highly popular benchmark. More importantly, we conduct comprehensive ablation studies over data, training, filtering, and rewarding strategies, thoroughly validating their effectiveness.

Haoyang Cui, Hao Jiang, Yadong Mu

As an important research task of human cultural heritage, the restoration of artworks and calligraphy is of great significance. Seldom existing works have taken the multi-source (i.e., fragments are not ensured to be from the same piece of artworks) fragment-oriented restoration task into account. We propose ShreddingNet, a coarse-to-fine two-stage pipeline for multi-source manuscript restoration that operates without restrictive conditions. The proposed coarse stage compares the features of each fragment, selecting top-K candidates and clustering fragments by source. This design leverages the key insight that erroneous matches rarely cross source boundaries, enabling high-precision clustering. The proposed fine-grained stage evaluates candidates, yielding matching scores and filters out erroneous matching pairs from the candidate set; producing more precise final matching pairs for global assembly. Experiments conducted on more than 4,000 images from two datasets demonstrate the average reconstruction F1-score achieves 98.37%, which is 5.72% higher than the current state-of-the-art method, confirming the method's effectiveness and robustness. Source code is available at github.com/tqychy/shreddingnet.