Stereo matching methods rely on dense pixel-wise ground truth labels, which are laborious to obtain, especially for real-world datasets. The scarcity of labeled data and domain gaps between synthetic and real-world images also pose notable challenges. In this paper, we propose a novel framework, BooSTer, that leverages both vision foundation models and large-scale mixed image sources, including synthetic, real, and single-view images. First, to fully unleash the potential of large-scale single-view images, we design a data generation strategy combining monocular depth estimation and diffusion models to generate dense stereo matching data from single-view images. Second, to tackle sparse labels in real-world datasets, we transfer knowledge from monocular depth estimation models, using pseudo-mono depth labels and a dynamic scale- and shift-invariant loss for additional supervision. Furthermore, we incorporate vision foundation model as an encoder to extract robust and transferable features, boosting accuracy and generalization. Extensive experiments on benchmark datasets demonstrate the effectiveness of our approach, achieving significant improvements in accuracy over existing methods, particularly in scenarios with limited labeled data and domain shifts.
论文检索
输入标题、作者或关键词，从 700 篇学术成果中精准定位
This study addresses the challenge of generating online 3D Gaussian Splatting (3DGS) models from RGB-only frames. Previous studies have employed dense SLAM techniques to estimate 3D scenes from keyframes for 3DGS model construction. However, these methods are limited by their reliance solely on keyframes, which are insufficient to capture an entire scene, resulting in incomplete reconstructions. Moreover, building a generalizable model requires incorporating frames from diverse viewpoints to achieve broader scene coverage. However, online processing restricts the use of many frames or extensive training iterations. Therefore, we propose a novel method for high-quality 3DGS modeling that improves model completeness through adaptive view selection. By analyzing reconstruction quality online, our approach selects optimal non-keyframes for additional training. By integrating both keyframes and selected non-keyframes, the method refines incomplete regions from diverse viewpoints, significantly enhancing completeness. We also present a framework that incorporates an online multi-view stereo approach, ensuring consistency in 3D information throughout the 3DGS modeling process. Experimental results demonstrate that our method outperforms state-of-the-art methods, delivering exceptional performance in complex outdoor scenes.
Vision-language models (VLMs) have demonstrated strong zero-shot inference capabilities but may exhibit stereotypical biases toward certain demographic groups. Consequently, downstream tasks leveraging these models may yield unbalanced performance across different target social groups, potentially reinforcing harmful stereotypes. Mitigating such biases is critical for ensuring fairness in practical applications. Existing debiasing approaches typically rely on curated face-centric datasets for fine-tuning or retraining, risking overfitting and limiting generalisability. To address this issue, we propose a novel framework, CABIN (Causal Adjustment Based INtervention). It leverages a causal framework to identify sensitive attributes in images as confounding factors. Employing a learned mapper, which is trained on general large-scale image-text pairs rather than face-centric datasets, CABIN may use text to adjust sensitive attributes in the image embedding, ensuring independence between these sensitive attributes and image embeddings. This independence enables a backdoor adjustment for unbiased inference without the drawbacks of additional fine-tuning or retraining on narrowly tailored datasets. Through comprehensive experiments and analyses, we demonstrate that CABIN effectively mitigates biases and improves fairness metrics while preserving the zero-shot strengths of VLMs. The code is available at: https://github.com/ipangbo/causal-debias
Exploring and Mitigating Implicit Bias in Large Language Models: A Cross-Domain Evaluation Framework
PDF ↗This paper investigates implicit biases in large language models (LLMs) triggered by subtle contextual cues. Through experiments, the study examines how these biases influence model outputs in domains such as healthcare and hiring. A framework for mitigating stereotype reinforcement is proposed, along with strategies to refine prompts and reduce biased responses. The goal is to improve fairness in AI-driven applications by addressing these biases and enhancing model equity.
The rise of large language models (LLMs) has revolutionized natural language processing, offering immense capabilities across various applications. The widespread integration of these models into commonplace technology has brought to light deep concerns about the biases they encompass, which could serve to perpetuate negative preconceptions and social injustices. The scope of my research includes social biases, brand biases, the impact of personas on bias, and stereotypes in low-resource languages. My contributions aim to deepen our understanding of these biases and develop methodologies to mitigate them, enhancing the fairness and utility of LLMs across diverse global applications.
Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent Framework
PDF ↗Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this problem by prompting LLMs to behave ethically, but this approach results in unacceptable performance degradation. In this paper, we propose a multi-objective approach within a multi-agent framework (MOMA) to mitigate social bias in LLMs without significantly compromising their performance. The key idea of MOMA involves deploying multiple agents to perform causal interventions on bias-related contents of the input questions, breaking the shortcut connection between these contents and the corresponding answers. Unlike traditional debiasing techniques leading to performance degradation, MOMA substantially reduces bias while maintaining accuracy in downstream tasks. Our experiments conducted in two datasets and two models demonstrate that MOMA reduces bias scores by up to 87.7%, with only a marginal performance degradation of up to 6.8% in the BBQ dataset. Additionally, it significantly enhances the multi-objective metric icat in the StereoSet dataset by up to 58.1%.
Semantic segmentation and 3D reconstruction are two fundamental tasks in remote sensing, typically treated as separate or loosely coupled tasks. Despite attempts to integrate them into a unified network, the constraints between the two heterogeneous tasks are not explicitly modeled, since the pioneering studies either utilize a loosely coupled parallel structure or engage in only implicit interactions, failing to capture the inherent connections. In this work, we explore the connections between the two tasks and propose a new network that imposes semantic constraints on the stereo matching task, both implicitly and explicitly. Implicitly, we transform the traditional parallel structure to a new cascade structure termed Semantic-Guided Cascade structure, where the deep features enriched with semantic information are utilized for the computation of initial disparity maps, enhancing semantic guidance. Explicitly, we propose a Semantic Selective Refinement (SSR) module and a Left-Right Semantic Consistency (LRSC) module. The SSR refines the initial disparity map under the guidance of the semantic map. The LRSC ensures semantic consistency between two views via reducing the semantic divergence after transforming the semantic map from one view to the other using the disparity map. Experiments on the US3D and WHU datasets demonstrate that our method achieves state-of-the-art performance for both semantic segmentation and stereo matching.
As a fundamental vision task, stereo matching has made remarkable progress. While recent iterative optimization-based methods have achieved promising performance, their feature extraction capabilities still have room for improvement. Inspired by the ability of vision foundation models (VFMs) to extract general representations, in this work, we propose AIO-Stereo which can flexibly select and transfer knowledge from multiple heterogeneous VFMs to a single stereo matching model. To better reconcile features between heterogeneous VFMs and the stereo matching model and fully exploit prior knowledge from VFMs, we proposed a dual-level feature utilization mechanism that aligns heterogeneous features and transfers multi-level knowledge. Based on the mechanism, a dual-level selective knowledge transfer module is designed to selectively transfer knowledge and integrate the advantages of multiple VFMs. Experimental results show that AIO-Stereo achieves start-of-the-art performance on multiple datasets and ranks 1st on the Middlebury dataset and outperforms all the published work on the ETH3D benchmark.
We present InstantSticker, a disentangled reconstruction pipeline based on Image-Based Lighting (IBL), which focuses on highly realistic decal blending, simulates stickers attached to the reconstructed surface, and allows for instant editing and real-time rendering. To achieve stereoscopic impression of the decal, we introduce shadow factor into IBL, which can be adaptively optimized during training. This allows the shadow brightness of surfaces to be accurately decomposed rather than baked into the diffuse color, ensuring that the edited texture exhibits authentic shading. To address the issues of warping and blurriness in previous methods, we apply As-Rigid-As-Possible (ARAP) parameterization to pre-unfold a specified area of the mesh and use the local UV mapping combined with a neural texture map to enhance the ability to express high-frequency details in that area. For instant editing, we utilize the Disney BRDF model, explicitly defining material colors with 3-channel diffuse albedo. This enables instant replacement of albedo RGB values during the editing process, avoiding the prolonged optimization required in previous approaches. In our experiment, we introduce the Ratio Variance Warping (RVW) metric to evaluate the local geometric warping of the decal area. Extensive experimental results demonstrate that our method surpasses previous decal blending methods in terms of editing quality, editing speed and rendering speed, achieving the state-of-the-art.
Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disparity characteristics inherent in stereo images, which leads to suboptimal rate-distortion results. In this paper, we propose a stereo image compression framework, named CAMSIC. CAMSIC independently transforms each image to latent representation and employs a powerful decoder-free Transformer entropy model to capture both spatial and disparity dependencies, by introducing a novel content-aware masked image modeling (MIM) technique. Our content-aware MIM facilitates efficient bidirectional interaction between prior information and estimated tokens, which naturally obviates the need for an extra Transformer decoder. Experiments show that our stereo image codec achieves state-of-the-art rate-distortion performance on two stereo image datasets Cityscapes and InStereo2K with fast encoding and decoding speed.
Recently, patch deformation-based methods have demonstrated significant strength in multi-view stereo by adaptively expanding the reception field of patches to help reconstruct textureless areas. However, such methods mainly concentrate on searching for pixels without matching ambiguity (i.e., reliable pixels) when constructing deformed patches, while neglecting the deformation instability caused by unexpected edge-skipping, resulting in potential matching distortions. Addressing this, we propose MSP-MVS, a method introducing multi-granularity segmentation prior for edge-confined patch deformation. Specifically, to avoid unexpected edge-skipping, we first aggregate and further refine multi-granularity depth edges gained from Semantic-SAM as prior to guide patch deformation within depth-continuous (i.e., homogeneous) areas. Moreover, to address attention imbalance caused by edge-confined patch deformation, we implement adaptive equidistribution and disassemble-clustering of correlative reliable pixels (i.e., anchors), thereby promoting attention-consistent patch deformation. Finally, to prevent deformed patches from falling into local-minimum matching costs caused by the fixed sampling pattern, we introduce disparity-sampling synergistic 3D optimization to help identify global-minimum matching costs. Evaluations on ETH3D and Tanks & Temples benchmarks prove our method obtains state-of-the-art performance with remarkable generalization.
Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. However, such approaches typically focus on exploring correlative reliable pixels to alleviate match ambiguity during patch deformation, but ignore the deformation instability caused by mistaken edge-skipping and visibility occlusion, leading to potential estimation deviation. To remedy the above issues, we propose DVP-MVS, which innovatively synergizes depth-edge aligned and cross-view prior for robust and visibility-aware patch deformation. Specifically, to avoid unexpected edge-skipping, we first utilize Depth Anything V2 followed by the Roberts operator to initialize coarse depth and edge maps respectively, both of which are further aligned through an erosion-dilation strategy to generate fine-grained homogeneous boundaries for guiding patch deformation. In addition, we reform view selection weights as visibility maps and restore visible areas by cross-view depth reprojection, then regard them as cross-view prior to facilitate visibility-aware patch deformation. Finally, we improve propagation and refinement with multi-view geometry consistency by introducing aggregated visible hemispherical normals based on view selection and local projection depth differences based on epipolar lines, respectively. Extensive evaluations on ETH3D and Tanks & Temples benchmarks demonstrate that our method can achieve state-of-the-art performance with excellent robustness and generalization.
Self-supervised stereo matching has drawn attention due to its ability to estimate disparity without needing ground-truth data. However, existing self-supervised stereo matching methods heavily rely on the photo-metric consistency assumption, which is vulnerable to natural disturbances, resulting in ambiguous supervision and inferior performance compared to the supervised ones. To relax the limitation of the photo-metric consistency assumption and even bypass this assumption, we propose a novel self-supervised framework named DualNet, which consists of two key steps: robust self-supervised teacher learning and pseudo-label supervised student training. Specifically, the teacher model is first trained in a self-supervised manner with a focus on feature-metric consistency and data augmentation consistency. Then, the output of the teacher model is geometrically constrained to obtain high-quality pseudo labels. Benefiting from these high-quality pseudo labels, the student model can outperform its teacher model by a large margin. With the two well-designed steps, the proposed framework DualNet ranks 1st among all self-supervised methods on multiple benchmarks, surprisingly even outperforming several supervised counterparts.
The scene flow estimation methods make significant progress by estimating pixel-wise 3D motion on implicitly learning a motion embedding using an end-to-end differentiable optimization framework. However, the motion embedding learned implicitly is insufficient for grouping pixels into rigid object in challenging regions, such as occlusion and inconsistent multi-view geometric properties. To address this issue, we propose a novel method for estimating scene flow called OAMaskFlow, which has three novelties. Firstly, we propose the concept of occlusion-aware motion (OAM) mask and generate the ground truth annotation through the photo-metric and geometry consistency. Secondly, we propose to supervise the motion embedding with the OAM mask to learn informative and reliable motion representation of the scene. Finally, a 3D motion propagation module is proposed to propagate high-quality 3D motion from reliable pixels to the challenging occluded regions. Experiments show that our proposed OAMaskFlow has reduced the EPE3D metric by 21.0% on the FlyingThings3D dataset and decreased SF-all metric by 24.3% on the KITTI scene flow benchmark than the baseline method RAFT-3D. Furthermore, we apply our proposed OAM mask in simultaneous localization and mapping (SLAM) to improve a state-of-the-art method DROID-SLAM. In comparison, the ATE metric has decreased by 65.7% and 58.3% on the TartanAir monocular and stereo datasets respectively.
Instruct Where the Model Fails: Generative Data Augmentation via Guided Self-contrastive Fine-tuning
PDF ↗Data augmentation is expected to bring about unseen features of training set, enhancing the model’s ability to generalize in situations where data is limited. Generative image models trained on large web-crawled datasets such as LAION are known to produce images with stereotypes and imperceptible bias when used to augment training data, owing to dataset misalignment and the generator’s ignorance of the downstream model. We improve downstream task awareness in generated images by proposing a task-aware fine-tuning strategy that actively detects failures of downstream task in the target model to fine-tune the generation process between epochs. The dynamic fine-tuning strategy is achieved by (1) inspecting misalignment between generated data and original data via VLM captioners and (2) adjusts both prompts and diffusion model so that the strategy dynamically guides the generator by focusing on the detected bias of VLM. This is done via re-captioning the overfitted data as well as finetuning the diffusion trajectory in a contrastive manner. To co-operate with the VLM captioner, the contrastive fine-tuning process dynamically adjusts different parts of the diffusion trajectory based on detected misalignment, thus shifting the the generated distribution away from making the downstream model overfit. Our experiments on few-shot class incremental learning show that our instruction-guided finetuning strategy consistently assists the downstream model with higher classification accuracy compared to generative data augmentation baselines such as Stable Diffusion and GPT-4o, and state-of-the-art non-generative strategies.
3D semantic scene completion is critical for multiple downstream tasks in autonomous systems. It estimates missing geometric and semantic information in the acquired scene data. Due to the challenging real-world conditions, this task usually demands complex models that process multi-modal data to achieve acceptable performance. We propose a unique neural model, leveraging advances from the state space and diffusion generative modeling to achieve remarkable 3D semantic scene completion performance with monocular image input. Our technique processes the data in the conditioned latent space of a variational autoencoder where diffusion modeling is carried out with an innovative state space technique. A key component of our neural network is the proposed Skimba (Skip Mamba) denoiser, which is adept at efficiently processing long-sequence data. The Skimba diffusion model is integral to our 3D scene completion network, incorporating a triple Mamba structure, dimensional decomposition residuals and varying dilations along three directions. We also adopt a variant of this network for the subsequent semantic segmentation stage of our method. Extensive evaluation on the standard SemanticKITTI and SSCBench-KITTI360 datasets show that our approach not only outperforms other monocular techniques by a large margin, it also achieves competitive performance against stereo methods.
Tri-Ergon: Fine-Grained Video-to-Audio Generation with Multi-Modal Conditions and LUFS Control
PDF ↗Video-to-audio (V2A) generation utilizes visual-only video features to produce realistic sounds that correspond to the scene. However, current V2A models often lack fine-grained control over the generated audio, especially in terms of loudness variation and the incorporation of multi-modal conditions. To overcome these limitations, we introduce Tri-Ergon, a diffusion-based V2A model that incorporates textual, auditory, and pixel-level visual prompts to enable detailed and semantically rich audio synthesis. Additionally, we introduce Loudness Units relative to Full Scale (LUFS) embedding, which allows for precise manual control of the loudness changes over time for individual audio channels, enabling our model to effectively address the intricate correlation of video and audio in real-world Foley workflows. Tri-Ergon is capable of creating 44.1 kHz high-fidelity stereo audio clips of varying lengths up to 60 seconds, which significantly outperforms existing state-of-the-art V2A methods that typically generate mono audio for a fixed duration.
FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-from-gradients
PDF ↗Surface-from-gradients (SfG) aims to recover a three-dimensional (3D) surface from its gradients. Traditional methods encounter significant challenges in achieving high accuracy and handling high-resolution inputs, particularly facing the complex nature of discontinuities and the inefficiencies associated with large-scale linear solvers. Although recent advances in deep learning, such as photometric stereo, have enhanced normal estimation accuracy, they do not fully address the intricacies of gradient-based surface reconstruction. To overcome these limitations, we propose a Fourier neural operator-based Numerical Integration Network (FNIN) within a two-stage optimization framework. In the first stage, our approach employs an iterative architecture for numerical integration, harnessing an advanced Fourier neural operator to approximate the solution operator in Fourier space. Additionally, a self-learning attention mechanism is incorporated to effectively detect and handle discontinuities. In the second stage, we refine the surface reconstruction by formulating a weighted least squares problem, addressing the identified discontinuities rationally. Extensive experiments demonstrate that our method achieves significant improvements in both accuracy and efficiency compared to current state-of-the-art solvers. This is particularly evident in handling high-resolution images with complex data, achieving errors of fewer than 0.1 mm on tested objects.
Learning-based multi-view stereo methods aim to predict depth maps for reconstructing dense point clouds. These methods rely on regularization to reduce redundancy in the cost volume. However, existing methods have limitations: CNN-based regularization is restricted to local receptive fields, while Transformer-based regularization struggles with handling depth discontinuities. These limitations often result in inaccurate depth maps with significant noise, particularly noticeable in the boundary and background regions. In this paper, we propose a Recurrent Regularization Transformer for Multi-View Stereo (RRT-MVS), which addresses these limitations by regularizing the cost volume separately for depth and spatial dimensions. Specifically, we introduce Recurrent Self-Attention (R-SA) to aggregate global matching costs within and across the cost maps and filter out noisy feature correlations. Additionally, we present Depth Residual Attention (DRA) to aggregate depth correlations within the cost volume and a Positional Adapter (PA) to enhance 3D positional awareness in each 2D cost map, further augmenting the effectiveness of R-SA. Experimental results demonstrate that RRT-MVS achieves state-of-the-art performance on the DTU and Tanks-and-Temples datasets. Notably, RRT-MVS ranks first on both the Tanks-and-Temples intermediate and advanced benchmarks among all published methods.
Egocentric human pose estimation (HPE) using wearable sensors is essential for VR/AR applications. Most methods rely solely on either egocentric-view images or sparse Inertial Measurement Unit (IMU) signals, leading to inaccuracies due to self-occlusion in images or the sparseness and drift of inertial sensors. Most importantly, the lack of real-world datasets containing both modalities is a major obstacle to progress in this field. To overcome the barrier, we propose EMHI, a multimodal Egocentric human Motion dataset with Head-Mounted Display (HMD) and body-worn IMUs, with all data collected under the real VR product suite. Specifically, EMHI provides synchronized stereo images from downward-sloping cameras on the headset and IMU data from body-worn sensors, along with pose annotations in SMPL format. This dataset consists of 885 sequences captured by 58 subjects performing 39 actions, totaling about 28.5 hours of recording. We evaluate the annotations by comparing them with optical marker-based SMPL fitting results. To substantiate the reliability of our dataset, we introduce MEPoser, a new baseline method for multimodal egocentric HPE, which employs a multimodal fusion encoder, temporal feature encoder, and MLP-based regression heads. The experiments on EMHI show that MEPoser outperforms existing single-modal methods and demonstrates the value of our dataset in solving the problem of egocentric HPE. We believe the release of EMHI and the method could advance the research of egocentric HPE and expedite the practical implementation of this technology in VR/AR products.