论文检索

Jierun Chen, Dongting Hu, Xijie Huang, Huseyin Coskun, Arpit Sahni, Aarush Gupta, Anujraaj Goyal, Dishani Lahiri, Rajesh Singh, Yerlan Idelbayev 等

Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to address all of these challenges by developing an extremely small and fast T2I model that generates high-resolution and high-quality images on mobile platforms. We propose several techniques to achieve this goal. First, we systematically examine the design choices of the network architecture to reduce model parameters and latency, while ensuring high-quality generation. Second, to further improve generation quality, we employ cross-architecture knowledge distillation from a much larger model, using a multi-level approach to guide the training of our model from scratch. Third, we enable a few-step generation by integrating adversarial guidance with knowledge distillation. Our model, for the first time, demonstrates the generation of 1024x1024 px images on a mobile device in 1.2 to 2.3 seconds. On ImageNet-1K, our model, with only 372M parameters, achieves an FID of 2.06 for 256x256 px generation. On T2I benchmarks (i.e., GenEval and DPG-Bench), our model with merely 379M parameters surpasses large-scale models with billions of parameters at a significantly smaller size (e.g., 7x smaller than SDXL, 14x smaller than IF-XL).

Hanbin Ko, Chang-Min Park

The development of large-scale image-text pair datasets has significantly advanced self-supervised learning in Vision-Language Processing (VLP). However, directly applying general-domain architectures such as CLIP to medical data presents challenges, particularly in handling negations and addressing the inherent data imbalance of medical datasets. To address these issues, we propose a novel approach that integrates clinically-enhanced dynamic soft labels and medical graphical alignment, thereby improving clinical comprehension and improving the applicability of contrastive loss in medical contexts. Furthermore, we introduce negation-based hard negatives to deepen the model's understanding of the complexities of clinical language. Our approach is easily integrated into medical CLIP training pipeline and achieves state-of-the-art performance across multiple tasks, including zero-shot, fine-tuned classification and report retrieval. To comprehensively evaluate our model's capacity in understanding clinical language, we introduce CXR-Align, a benchmark uniquely designed to evaluate the understanding of negation and clinical information within chest X-ray (CXR) datasets. Experimental results demonstrate that our proposed methods are straightforward to implement and generalize effectively across contrastive learning frameworks, enhancing medical VLP capabilities and advancing clinical language understanding in medical imaging.

Barza Nisar, Steven L. Waslander

Self-supervised learning (SSL) on 3D point clouds has the potential to learn feature representations that can transfer to diverse sensors and multiple downstream perception tasks. However, recent SSL approaches fail to define pretext tasks that retain geometric information such as object pose and scale, which can be detrimental to the performance of downstream localization and geometry-sensitive 3D scene understanding tasks, such as 3D semantic segmentation and 3D object detection. We propose PSA-SSL, a novel extension to point cloud SSL that learns object pose and size-aware (PSA) features. Our approach defines a self-supervised bounding box regression pretext task, which retains object pose and size information. Furthermore, we incorporate LiDAR beam pattern augmentation on input point clouds, which encourages learning sensor-agnostic features. Our experiments demonstrate that with a single pretrained model, our light-weight yet effective extensions achieve significant improvements on 3D semantic segmentation with limited labels across popular autonomous driving datasets (Waymo, nuScenes, SemanticKITTI). Moreover, our approach outperforms other state-of-the-art SSL methods on 3D semantic segmentation (using up to 10 times less labels), as well as on 3D object detection. Our code will be released on https://github.com/TRAILab/PSA-SSL.

Mingfei Han, Liang Ma, Kamila Zhumakhanova, Ekaterina Radionova, Jingyi Zhang, Xiaojun Chang, Xiaodan Liang, Ivan Laptev

Vision-and-Language Navigation (VLN) suffers from the limited diversity and scale of training data, primarily constrained by the manual curation of existing simulators.To address this, we introduce RoomTour3D, a video-instruction dataset derived from web-based room tour videos that capture real-world indoor spaces and human walking demonstrations. Unlike existing VLN datasets, RoomTour3D leverages the scale and diversity of online videos to generate open-ended human walking trajectories and open-world navigable instructions. To compensate for the lack of navigation data in online videos, we perform 3D reconstruction and obtain 3D trajectories of walking paths augmented with additional information on the room types, object locations and 3D shape of surrounding scenes. Our dataset includes ~100K open-ended description-enriched trajectories with ~200K instructions, and 17K action-enriched trajectories from 1847 room tour environments.We demonstrate experimentally that RoomTour3D enables significant improvements across multiple VLN tasks including CVDN, SOON, R2R, and REVERIE.Moreover, RoomTour3D facilitates the development of trainable zero-shot VLN agents, showcasing the potential and challenges of advancing towards open-world navigation.

Xiaoying Xing, Avinab Saha, Junfeng He, Susan Hao, Paul Vicol, Moonkyung Ryu, Gang Li, Sahil Singla, Sarah Young, Yinxiao Li 等

Text-to-image (T2I) generation has made significant advances in recent years, but challenges still remain in the generation of perceptual artifacts, misalignment with complex prompts, and safety. The prevailing approach to address these issues involves collecting human feedback on generated images, training reward models to estimate human feedback, and then fine-tuning T2I models based on the reward models to align them with human preferences. However, while existing reward fine-tuning methods can produce images with higher rewards, they may change model behavior in unexpected ways. For example, fine-tuning for one quality aspect (e.g., safety) may degrade other aspects (e.g., prompt alignment), or may lead to reward hacking (e.g., finding a way to increase rewards without having the intended effect). In this paper, we propose Focus-N-Fix, the first region-aware fine-tuning method that trains models to correct only previously problematic image regions. The resulting fine-tuned model generates images with the same high-level structure as the original model but shows significant improvements in regions where the original model was deficient in safety (over-sexualization and violence), plausibility, or other criteria. Our experiments demonstrate that Focus-N-Fix improves these localized quality aspects with little or no degradation to others and typically imperceptible changes in the rest of the image. Disclaimer: This paper contains images that may be overly sexual, violent, offensive or harmful.

Yan Xie, Zequn Zeng, Hao Zhang, Yucheng Ding, Yi Wang, Zhengjue Wang, Bo Chen, Hongwei Liu

Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. Existing CBMs just learn coarse-grained relations between the whole image and the concepts, less considering local image information, leading to two main drawbacks: i) they often produce spurious visual-concept relations, hence decreasing model reliability; and ii) though CBMs could explain the importance of every concept to the final prediction, it is still challenging to tell which visual region produces the prediction. To solve these problems, this paper proposes a Disentangled Optimal Transport CBM (DOT-CBM) framework to explore fine-grained visual-concept relations between local image patches and concepts. Specifically, we model the concept prediction process as a transportation problem between the patches and concepts, thereby achieving explicit fine-grained feature alignment. We also incorporate orthogonal projection losses within the modality to enhance local feature disentanglement. To further address the shortcut issues caused by statistical biases in the data, we utilize the visual saliency map and concept label statistics as transportation priors. Thus, DOT-CBM can visualize inversion heatmaps, provide more reliable concept predictions, and produce more accurate class predictions. Comprehensive experiments demonstrate that our proposed DOT-CBM achieves SOTA performance on several tasks, including image classification, local part detection and out-of-distribution generalization.

Zixuan Huang, Mark Boss, Aaryaman Vasishta, James M. Rehg, Varun Jampani

We study the problem of single-image 3D object reconstruction. Recent works have diverged into two directions: regression-based modeling and generative modeling. Regression methods efficiently infer visible surfaces, but struggle with occluded regions. Generative methods handle uncertain regions better by modeling distributions, but are computationally expensive and the generation is often misaligned with visible surfaces. In this paper, we present SPAR3D, a novel two-stage approach aiming to take the best of both directions. The first stage of SPAR3D generates sparse 3D point clouds using a lightweight point diffusion model, which has a fast sampling speed. The second stage uses both the sampled point cloud and the input image to create highly detailed meshes. Our two-stage design enables probabilistic modeling of the ill-posed single-image 3D task while maintaining high computational efficiency and great output fidelity. Using point clouds as an intermediate representation further allows for interactive user edits. Evaluated on diverse datasets, SPAR3D demonstrates superior performance over previous state-of-the-art methods, at an inference speed of 0.7 seconds. Project page with code and model: https://spar3d.github.io

Yifan Chang, Junjie Huang, Xiaofeng Wang, Yun Ye, Zhujin Liang, Yi Shan, Dalong Du, Xingang Wang

Monocular 3D lane detection is a fundamental task in autonomous driving. Although sparse-point methods lower computational load and maintain high accuracy in complex lane geometries, current methods fail to fully leverage the geometric structure of lanes in both lane geometry representations and model design. In lane geometry representations, we present a theoretical analysis alongside experimental validation to verify that current sparse lane representation methods contain inherent flaws, resulting in potential errors of up to 20 m, which raise significant safety concerns for driving. To address this issue, we propose a novel patching strategy to completely represent the full lane structure. To enable existing models to match this strategy, we introduce the EndPoint head (EP-head), which adds a patching distance to endpoints. The EP-head enables the model to predict more complete lane representations even with fewer preset points, effectively addressing existing limitations and paving the way for models that are faster and require fewer parameters in the future. In model design, to enhance the model's perception of lane structures, we propose the PointLane attention (PL-attention), which incorporates prior geometric knowledge into the attention mechanism. Extensive experiments demonstrate the effectiveness of the proposed methods on various state-of-the-art models. For instance, in terms of the overall F1-score, our methods improve Persformer by 4.4 points, Anchor3DLane by 3.2 points, and LATR by 2.8 points. The code will be available soon.

Haeyun Choi, Heemin Yang, Janghyeok Han, Sunghyun Cho

In this paper, we propose DeepDeblurRF, a novel radiance field deblurring approach that can synthesize high-quality novel views from blurred training views with significantly reduced training time. DeepDeblurRF leverages deep neural network (DNN)-based deblurring modules to enjoy their deblurring performance and computational efficiency. To effectively combine DNN-based deblurring and radiance field construction, we propose a novel radiance field (RF)-guided deblurring and an iterative framework that performs RF-guided deblurring and radiance field construction in an alternating manner. Moreover, DeepDeblurRF is compatible with various scene representations, such as voxel grids and 3D Gaussians, expanding its applicability. We also present BlurRF-Synth, the first large-scale synthetic dataset for training radiance field deblurring frameworks. We conduct extensive experiments on both camera motion blur and defocus blur, demonstrating that DeepDeblurRF achieves state-of-the-art novel-view synthesis quality with significantly reduced training time.

Ziyuan Yang, Yingyu Chen, Zhiwen Wang, Hongming Shan, Yang Chen, Yi Zhang

Reducing radiation doses benefits patients, but the resultant low-dose computed tomography (LDCT) images often suffer from clinically unacceptable noise and artifacts. While deep learning (DL) has shown promise in LDCT reconstruction, it requires large-scale data collection from multiple clients, raising privacy concerns. Federated learning (FL) has been introduced to mitigate these privacy concerns; however, current methods are typically tailored to specific scanning protocols, which limits their generalizability and makes them less effective for unseen protocols. To address these issues, we propose SCAN-PhysFed, a novel SCanning- and ANatomy-level personalized Physics-Driven Federated learning paradigm for LDCT reconstruction. Since the noise distribution in LDCT data is closely tied to scanning protocols and anatomical structures, we propose a dual-level physics-informed way to address these challenges. Specifically, we incorporate physical and anatomical prompts into our physics-informed hypernetworks to capture scanning- and anatomy-specific information, enabling dual-level physics-driven personalization of imaging features. These prompts are derived from the scanning protocol and the radiology report generated by a medical large language model (MLLM). Subsequently, client-specific decoders project these dual-level personalized imaging features back into the image domain. Besides, to tackle the challenge of unseen data, we introduce a novel protocol vector-quantization strategy (PVQS), which ensures consistent performance across new clients by quantifying unseen scanning codes to the closest match in the scanning codebook. Extensive experimental results demonstrate the superior performance of SCAN-PhysFed on public datasets.

Yun Chang, Leonor Fermoselle, Duy Ta, Bernadette Bucher, Luca Carlone, Jiuguang Wang

While recent work in scene reconstruction and understanding has made strides in grounding natural language to physical 3D environments, it is still challenging to ground abstract, high-level instructions to a 3D scene. High-level instructions might not explicitly invoke semantic elements in the scene, and even the process of breaking a high-level task into a set of more concrete subtasks --a process called hierarchical task analysis-- is environment-dependent. In this work, we propose ASHiTA, the first framework that generates a task hierarchy grounded to a 3D scene graph by breaking down high-level tasks into grounded subtasks. ASHiTA alternates LLM-assisted hierarchical task analysis --to generate the task breakdown-- with task-driven scene graph construction to generate a suitable representation of the environment. Our experiments show that ASHiTA performs significantly better than LLM baselines in breaking down high-level tasks into environment-dependent subtasks and is additionally able to achieve grounding performance comparable to state-of-the-art methods

Lei Li, Yuancheng Wei, Zhihui Xie, Xuqing Yang, Yifan Song, Peiyi Wang, Chenxin An, Tianyu Liu, Sujian Li, Bill Yuchen Lin 等

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference labels from traditional VL tasks, which can introduce biases and often fail to effectively challenge state-of-the-art models. To address these limitations, we introduce VL-RewardBench, a comprehensive benchmark spanning general multimodal queries, visual hallucination detection, and complex reasoning tasks. Through our AI-assisted annotation pipeline that combines sample selection with human verification, we curate 1,250 high-quality examples specifically designed to probe VL-GenRMs limitations. Comprehensive evaluation across 16 leading large vision-language models demonstrates VL-RewardBench's effectiveness as a challenging testbed, where even GPT-4o achieves only 65.4% accuracy, and state-of-the-art open-source models such as Qwen2-VL-72B, struggle to surpass random-guessing. Importantly, performance on VL-RewardBench strongly correlates (Pearson's r > 0.9) with MMMU-Pro accuracy using Best-of-N sampling with VL-GenRMs. Analysis experiments uncover three critical insights for improving VL-GenRMs: (i) models predominantly fail at basic visual perception tasks rather than reasoning tasks; (ii) inference-time scaling benefits vary dramatically by model capacity; and (iii) training VL-GenRMs to learn to judge substantially boosts judgment capability (+14.7% accuracy for a 7B VL-GenRM). We believe VL-RewardBench along with the experimental insights will become a valuable resource for advancing VL-GenRMs. Project page: https://vl-rewardbench.github.io

Wenhuan Huang, Yi JI, Guiqian Zhu, Li Ying, Chunping Liu

In scene graph generation (SGG), the accurate prediction of unseen triples is essential for its effectiveness in downstream vision-language tasks. We hypothesize that the predicates of unseen triples can be viewed as transformations of seen predicates in feature space, and the essence of the zero-shot task is to bridge the gap caused by this transformation. Traditional models, however, have difficulty addressing this challenge, which we attribute to their inability to model the predicates equivariant. To overcome this limitation, we introduce a novel framework based on capsule networks (CAPSGG). We propose a Three-Stream Pipeline that generates modality-specific representations for predicates, while building low-level predicate capsules of these modalities. Then these capsules are aggregated into high-level predicate capsules using a Routing Capsule Layer. In addition, we introduce GroupLoss to aggregate capsules with the same predicate label into groups. This replaces the global loss with the intra-group loss, effectively balancing the learning of predicate invariance and equivariant features, while mitigating the impact of the severe long-tail distribution of the predicate categories. Our extensive experiments demonstrate the notable superiority of our approach over state-of-the-art methods, with zero-shot indicators outperforming up to 132.26% on SGCls task than the T-CAR [21]. Our code will be available upon publication.

Ziyu Yao, Xuxin Cheng, Zhiqi Huang, Lei Li

Repetitive action counting, which aims to count periodic movements in a video, is valuable for video analysis applications such as fitness monitoring. However, existing methods largely rely on regression networks with limited representational capacity, which hampers their ability to accurately capture variable periodic patterns. Additionally, their supervised learning on narrow, limited training sets leads to overfitting and restricts their ability to generalize across diverse scenarios. To address these challenges, we propose CountLLM, the first large language model (LLM)-based framework that takes video data and periodic text prompts as inputs and outputs the desired counting value. CountLLM leverages the rich clues from explicit textual instructions and the powerful representational capabilities of pre-trained LLMs for repetitive action counting. To effectively guide CountLLM, we develop a periodicity-based structured template for instructions that describes the properties of periodicity and implements a standardized answer format to ensure consistency. Additionally, we propose a progressive multimodal training paradigm to enhance the periodicity-awareness of the LLM. Empirical evaluations on widely recognized benchmarks demonstrate CountLLM's superior performance and generalization, particularly in handling novel and out-of-domain actions that deviate significantly from the training data, offering a promising avenue for repetitive action counting.

Zhenqi Dai, Ting Liu, Yanning Zhang

Efficient 3D scene representation has become a key challenge with the rise of 3D Gaussian Splatting (3DGS), particularly when incorporating semantic information into the scene representation. Existing 3DGS-based methods embed both color and high-dimensional semantic features into a single field, leading to significant storage and computational overhead. To mitigate this, we propose Decoupled Feature 3D Gaussian Splatting (DF-3DGS), a novel method that decouples the color and semantic fields, thereby reducing the number of 3D Gaussians required for semantic representation. We then introduce a hierarchical compression strategy that first employs our novel quantization approach with dynamic codebook evolution to reduce data size, followed by a scene-specific autoencoder for further compression of the semantic feature dimensions. This multi-stage approach results in a compact representation that enhances both storage efficiency and reconstruction speed. Experimental results demonstrate that DF-3DGS outperforms previous 3DGS-based methods, achieving faster training and rendering times while requiring less storage, without sacrificing performance--in fact, it improves performance in the novel view semantic segmentation task. Specifically, DF-3DGS achieves remarkable improvements over Feature 3DGS, reducing training time by 10xand storage by 20x, while improving the mIoU of novel view semantic segmentation by 4%. The code will be publicly available.

Saksham Singh Kushwaha, Yapeng Tian

Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds aligning with onscreen objects, while V2A cannot generate semantically complete (offscreen sounds missing). In this work, we address the task of holistic audio generation: given a video and a text prompt, we aim to generate both onscreen and offscreen sounds that are temporally synchronized with the video and semantically aligned with text and video. Previous approaches for joint text and video-to-audio generation often suffer from modality bias, favoring one modality over the other. To overcome this limitation, we introduce VinTAGe, a flow-based transformer model that jointly considers text and video to guide audio generation. Our framework comprises two key components: a Visual-Text Encoder and a Joint VT-SiT model. To reduce modality bias and improve generation quality, we employ pretrained uni-modal text-to-audio and video-to-audio generation models for additional guidance. Due to the lack of appropriate benchmarks, we also introduce VinTAGe-Bench, a dataset of 636 video-text-audio pairs containing both onscreen and offscreen sounds. Our comprehensive experiments on VinTAGe-Bench demonstrate that joint text and visual interaction is necessary for holistic audio generation. Furthermore, VinTAGe achieves state-of-the-art results on the VGGSound benchmark.We will release our pretrained models and the VinTAGe-Bench dataset to facilitate future research in this exciting field.

Jiang Wu, Rui Li, Yu Zhu, Rong Guo, Jinqiu Sun, Yanning Zhang

We present a Gaussian Splatting method for surface reconstruction using sparse input views. Previous methods relying on dense views struggle with extremely sparse Structure-from-Motion points for initialization. While learning-based Multi-view Stereo (MVS) provides dense 3D points, directly combining it with Gaussian Splatting leads to suboptimal results due to the ill-posed nature of sparse-view geometric optimization. We propose Sparse2DGS, an MVS-initialized Gaussian Splatting pipeline for complete and accurate reconstruction. Our key insight is to incorporate the geometric-prioritized enhancement schemes, allowing for direct and robust geometric learning under ill-posed conditions. Sparse2DGS outperforms existing methods by notable margins, with 1.13 Chamfer Distance error compared to 2DGS (2.81) on the DTU dataset using 3 views. Meanwhile, our method is 2x faster than NeRF-based fine-tuning approach. Code is available at https://github.com/Wuuu3511/Sparse2DGS.

Yangming Zhang, Wenqi Jia, Wei Niu, Miao Yin

3D Gaussian Splatting (3DGS) has emerged as a mainstream for novel view synthesis, leveraging continuous aggregations of Gaussian functions to model scene geometry. However, 3DGS suffers from substantial memory requirements to store the large amount of Gaussians, hindering its efficiency and practicality. To address this challenge, we introduce GaussianSpa, an optimization-based simplification framework for compact and high-quality 3DGS. Specifically, we formulate the simplification objective as a constrained optimization problem associated with the 3DGS training. Correspondingly, we propose an efficient "optimizing-sparsifying" solution for the formulated problem, alternately solving two independent sub-problems and gradually imposing substantial sparsity onto the Gaussians in the 3DGS training process. We conduct quantitative and qualitative evaluations on various datasets, demonstrating the superiority of GaussianSpa over existing state-of-the-art approaches. Notably, GaussianSpa achieves an average PSNR improvement of 0.9 dB on the real-world Deep Blending dataset with 10X fewer Gaussians compared to the vanilla 3DGS.

Yue Fan, Ningjing Fan, Ivan Skorokhodov, Oleg Voynov, Savva Ignatyev, Evgeny Burnaev, Peter Wonka, Yiqun Wang

We develop a method that recovers the surface, materials, and illumination of a scene from its posed multi-view images. In contrast to prior work, it does not require any additional data and can handle glossy objects or bright lighting. It is a progressive inverse rendering approach, which consists of three stages. In the first stage, we reconstruct the scene radiance and signed distance function (SDF) with a novel regularization strategy for specular reflections. We propose to explain a pixel color using both surface and volume rendering jointly, which allows for handling complex view-dependent lighting effects for surface reconstruction. In the second stage, we distill light visibility and indirect illumination from the learned SDF and radiance field using learnable mapping functions. Finally, we design a method for estimating the ratio of incoming direct light reflected in a specular manner and use it to reconstruct the materials and direct illumination. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art in recovering surfaces, materials, and lighting without relying on any additional data.

Hanrui Zhao, Niuniu Qi, Mengxin Ren, Banglong Liu, Shuming Shi, Zhengfeng Yang

Polynomial Lyapunov function \mathcal V (x) provides mathematically rigorous that converts stability analysis into efficiently solvable optimization problem. Traditional numerical methods rely on user-defined templates, while emerging neural \mathcal V (x) offer flexibility but exhibit poor generalization yield from naive Square polynomial networks. In this paper, we propose a novel learning-enabled polynomial \mathcal V (x) synthesis approach, where a data-driven machine learning process guided by target-based sampling to fit candidate \mathcal V (x) which naturally compatible with the sum-of-squares (SOS) soundness verification. The framework is structured as an iterative loop between a Learner and a Verifier , where the Learner trains expressive polynomial \mathcal V (x) network via polynomial expansions, while the Verifier encodes learned candidates with SOS constraints to identify a real \mathcal V (x) by solving LMI feasibility test problems. The entire procedure is driven by a high-accuracy counterexample guidance technique to further enhance efficiency. Experimental results demonstrate that our approach outperforms both SMT-based polynomial neural Lyapunov function synthesis and traditional SOS method.