Fully Exploiting Vision Foundation Model's Profound Prior Knowledge for Generalizable RGB-Depth Driving Scene Parsing

Recent vision foundation models (VFMs), typically based on Vision Transformer (ViT), have significantly advanced numerous computer vision tasks. Despite their success in tasks focused solely on RGB images, the potential of VFMs in RGB-depth driving scene parsing remains largely under-explored. In this article, we take one step toward this emerging research area by investigating a feasible technique to fully exploit VFMs for generalizable RGB-depth driving scene parsing. Specifically, we explore the inherent characteristics of RGB and depth data, thereby presenting a Heterogeneous Feature Integration Transformer (HFIT). This network enables the efficient extraction and integration of comprehensive heterogeneous features without re-training ViTs. Relative depth prediction results from VFMs, used as inputs to the HFIT side adapter, overcome the limitations of the dependence on depth maps. Our proposed HFIT demonstrates superior performance compared to all other traditional single-modal and data-fusion scene parsing networks, pre-trained VFMs, and ViT adapters on the Cityscapes and KITTI Semantics datasets. We believe this novel strategy paves the way for future innovations in VFM-based data-fusion techniques for driving scene parsing. Our source code is publicly available at https://mias.group/HFIT.

CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation

Category-level object pose estimation aims to recover the rotation, translation and size of unseen instances within predefined categories. In this task, deep neural network-based methods have demonstrated remarkable performance. However, previous studies show they suffer from spurious correlations raised by "unclean" confounders in models, hindering their performance on novel instances with significant variations. To address this issue, we propose CleanPose, a novel approach integrating causal learning and knowledge distillation to enhance category-level pose estimation. To mitigate the negative effect of unobserved confounders, we develop a causal inference module based on front-door adjustment, which promotes unbiased estimation by reducing potential spurious correlations. Additionally, to further improve generalization ability, we devise a residual-based knowledge distillation method that has proven effective in providing comprehensive category information guidance. Extensive experiments across multiple benchmarks (REAL275, CAMERA25 and HouseCat6D) hightlight the superiority of proposed CleanPose over state-of-the-art methods. Code will be released.

These Maps Are Made by Propagation: Adapting Deep Stereo Networks to Road Scenarios with Decisive Disparity Diffusion

Stereo matching has emerged as a cost-effective solution for road surface 3D reconstruction, garnering significant attention towards improving both computational efficiency and accuracy. This article introduces decisive disparity diffusion (D3Stereo), marking the first exploration of dense deep feature matching that adapts pre-trained deep convolutional neural networks (DCNNs) to previously unseen road scenarios. A pyramid of cost volumes is initially created using various levels of learned representations. Subsequently, a novel recursive bilateral filtering algorithm is employed to aggregate these costs. A key innovation of D3Stereo lies in its alternating decisive disparity diffusion strategy, wherein intra-scale diffusion is employed to complete sparse disparity images, while inter-scale inheritance provides valuable prior information for higher resolutions. Extensive experiments conducted on our created UDTIRI-Stereo and Stereo-Road datasets underscore the effectiveness of D3Stereo strategy in adapting pre-trained DCNNs and its superior performance compared to all other explicit programming-based algorithms designed specifically for road surface 3D reconstruction. Additional experiments conducted on the Middlebury dataset with backbone DCNNs pre-trained on the ImageNet database further validate the versatility of D3Stereo strategy in tackling general stereo matching problems.

MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer

Transferring visual-language knowledge from large-scale foundation models for video recognition has proved to be effective. To bridge the domain gap, additional parametric modules are added to capture the temporal information. However, zero-shot generalization diminishes with the increase in the number of specialized parameters, making existing works a trade-off between zero-shot and close-set performance. In this paper, we present MoTE, a novel framework that enables generalization and specialization to be balanced in one unified model. Our approach tunes a mixture of temporal experts to learn multiple task views with various degrees of data fitting. To maximally preserve the knowledge of each expert, we propose \emph{Weight Merging Regularization}, which regularizes the merging process of experts in weight space. Additionally with temporal feature modulation to regularize the contribution of temporal feature during test. We achieve a sound balance between zero-shot and close-set video recognition tasks and obtain state-of-the-art or competitive results on various datasets, including Kinetics-400 \& 600, UCF, and HMDB. Code is available at \url{https://github.com/ZMHH-H/MoTE}.

RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion

Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps and fuses these features through attention mechanisms, demonstrating compelling efficacy in RGB-Normal road scene parsing. However, its performance significantly deteriorates when handling other types/sources of data or performing more universal, all-category scene parsing tasks. To overcome these limitations, this study introduces RoadFormer+, an efficient, robust, and adaptable model capable of effectively fusing RGB-X data, where ``X'', represents additional types/modalities of data such as depth, thermal, surface normal, and polarization. Specifically, we propose a novel hybrid feature decoupling encoder to extract heterogeneous features and decouple them into global and local components. These decoupled features are then fused through a dual-branch multi-scale heterogeneous feature fusion block, which employs parallel Transformer attentions and convolutional neural network modules to merge multi-scale features across different scales and receptive fields. The fused features are subsequently fed into a decoder to generate the final semantic predictions. Notably, our proposed RoadFormer+ ranks first on the KITTI Road benchmark and achieves state-of-the-art performance in mean intersection over union on the Cityscapes, MFNet, FMB, and ZJU datasets. Moreover, it reduces the number of learnable parameters by 65\% compared to RoadFormer. Our source code will be publicly available at mias.group/RoadFormerPlus.

Bootstrapping Vision-language Models for Self-supervised Remote Physiological Measurement

Facial video-based remote physiological measurement is a promising research area for detecting human vital signs (e.g., heart rate, respiration frequency) in a non-contact way. Conventional approaches are mostly supervised learning, requiring extensive collections of facial videos and synchronously recorded photoplethysmography (PPG) signals. To tackle it, self-supervised learning has recently gained attentions; due to the lack of ground truth PPG signals, its performance is however limited. In this paper, we propose a novel self-supervised framework that successfully integrates the popular vision-language models (VLMs) into the remote physiological measurement task. Given a facial video, we first augment its positive and negative video samples with varying rPPG signal frequencies. Next, we introduce a frequency-oriented vision-text pair generation method by carefully creating contrastive spatio-temporal maps from positive and negative samples and designing proper text prompts to describe their relative ratios of signal frequencies. A pre-trained VLM is employed to extract features for these formed vision-text pairs and estimate rPPG signals thereafter. We develop a series of generative and contrastive learning mechanisms to optimize the VLM, including the text-guided visual map reconstruction task, the vision-text contrastive learning task, and the frequency contrastive and ranking task. Overall, our method for the first time adapts VLMs to digest and align the frequency-related knowledge in vision and text modalities. Extensive experiments on four benchmark datasets demonstrate that it significantly outperforms state of the art self-supervised methods.

SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning

Unsupervised monocular depth estimation frameworks have shown promising performance in autonomous driving. However, existing solutions primarily rely on a simple convolutional neural network for ego-motion recovery, which struggles to estimate precise camera poses in dynamic, complicated real-world scenarios. These inaccurately estimated camera poses can inevitably deteriorate the photometric reconstruction and mislead the depth estimation networks with wrong supervisory signals. In this article, we introduce SCIPaD, a novel approach that incorporates spatial clues for unsupervised depth-pose joint learning. Specifically, a confidence-aware feature flow estimator is proposed to acquire 2D feature positional translations and their associated confidence levels. Meanwhile, we introduce a positional clue aggregator, which integrates pseudo 3D point clouds from DepthNet and 2D feature flows into homogeneous positional representations. Finally, a hierarchical positional embedding injector is proposed to selectively inject spatial clues into semantic features for robust camera pose decoding. Extensive experiments and analyses demonstrate the superior performance of our model compared to other state-of-the-art methods. Remarkably, SCIPaD achieves a reduction of 22.2\% in average translation error and 34.8\% in average angular error for camera pose estimation task on the KITTI Odometry dataset. Our source code is available at \url{https://mias.group/SCIPaD}.

MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation

Despite the remarkable developments of recent large models in Embodied Artificial Intelligence (E-AI), their integration into robotics is hampered by their excessive parameter sizes and computational demands. Towards the Vision-and-Language Navigation (VLN) task, a core task in E-AI, this paper reveals the great potential of using knowledge distillation for obtaining lightweight student models by proposing a Meta-Ability Guided Interactive Chain-of-distillation (MAGIC) method. Specifically, a Meta-Ability Knowledge Distillation (MAKD) framework is proposed for decoupling and refining the necessary meta-abilities of VLN agents. A Meta-Knowledge Randomization Weighting (MKRW) and a Meta-Knowledge Transferable Determination (MKTD) module are incorporated to dynamically adjust aggregation weights at the meta-ability and sample levels, respectively. Move beyond the traditional one-step unidirectional distillation, an Interactive Chain-of-Distillation (ICoD) learning strategy is proposed to allow students to give feedback to teachers, forming a new multi-step teacher-student co-evolution pipeline. Remarkably, on the R2R test unseen public leaderboard, our smallest model, MAGIC-S, with only 5% (11M) of the teacher's size, outperforms all previous methods under the same training data. Additionally, our largest model, MAGIC-L, surpasses the previous state-of-the-art by 5.84% in SPL and 3.18% in SR. Furthermore, a new dataset was collected and annotated from our living environments, where MAGIC-S demonstrated superior performance and real-time efficiency. Our code is publicly available on https://github.com/CrystalSixone/VLN-MAGIC.

SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection

Visual anomaly detection is vital in real-world applications, such as industrial defect detection and medical diagnosis. However, most existing methods focus on local structural anomalies and fail to detect higher-level functional anomalies under logical conditions. Although recent studies have explored logical anomaly detection, they can only address simple anomalies like missing or addition and show poor generalizability due to being heavily data-driven. To fill this gap, we propose SAM-LAD, a zero-shot, plug-and-play framework for logical anomaly detection in any scene. First, we obtain a query image's feature map using a pre-trained backbone. Simultaneously, we retrieve the reference images and their corresponding feature maps via the nearest neighbor search of the query image. Then, we introduce the Segment Anything Model (SAM) to obtain object masks of the query and reference images. Each object mask is multiplied with the entire image's feature map to obtain object feature maps. Next, an Object Matching Model (OMM) is proposed to match objects in the query and reference images. To facilitate object matching, we further propose a Dynamic Channel Graph Attention (DCGA) module, treating each object as a keypoint and converting its feature maps into feature vectors. Finally, based on the object matching relations, an Anomaly Measurement Model (AMM) is proposed to detect objects with logical anomalies. Structural anomalies in the objects can also be detected. We validate our proposed SAM-LAD using various benchmarks, including industrial datasets (MVTec Loco AD, MVTec AD), and the logical dataset (DigitAnatomy). Extensive experimental results demonstrate that SAM-LAD outperforms existing SoTA methods, particularly in detecting logical anomalies.

DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation

There has been a recent surge of interest in learning to perceive depth from monocular videos in an unsupervised fashion. A key challenge in this field is achieving robust and accurate depth estimation in challenging scenarios, particularly in regions with weak textures or where dynamic objects are present. This study makes three major contributions by delving deeply into dense correspondence priors to provide existing frameworks with explicit geometric constraints. The first novelty is a contextual-geometric depth consistency loss, which employs depth maps triangulated from dense correspondences based on estimated ego-motion to guide the learning of depth perception from contextual information, since explicitly triangulated depth maps capture accurate relative distances among pixels. The second novelty arises from the observation that there exists an explicit, deducible relationship between optical flow divergence and depth gradient. A differential property correlation loss is, therefore, designed to refine depth estimation with a specific emphasis on local variations. The third novelty is a bidirectional stream co-adjustment strategy that enhances the interaction between rigid and optical flows, encouraging the former towards more accurate correspondence and making the latter more adaptable across various scenarios under the static scene hypotheses. DCPI-Depth, a framework that incorporates all these innovative components and couples two bidirectional and collaborative streams, achieves state-of-the-art performance and generalizability across multiple public datasets, outperforming all existing prior arts. Specifically, it demonstrates accurate depth estimation in texture-less and dynamic regions, and shows more reasonable smoothness.