WACV 2024 论文列表

Room layout estimation predicts layouts from a single panorama. It requires datasets with large-scale and diverse room shapes to well train the models. However, there are significant imbalances in real-world datasets including the dimensions of layout complexity, camera locations, and variation in scene appearance. These issues considerably influence the model training performance. In this work, we propose imBalance-Aware Room Layout Estimation (iBARLE) framework to address these issues. iBARLE consists of: (1) Appearance Variation Generation (AVG) module, which promotes visual appearance domain generalization, (2) Complex Structure Mix-up (CSMix) module, which enhances generalizability w.r.t. room structure, and (3) a gradient-based layout objective function, which allows more effective accounting for occlusions in complex layouts. All modules are jointly trained and help each other to achieve the best performance. Experiments and ablation studies based on ZInD dataset illustrate that iBARLE has state-of-the-art performance compared with other layout estimation baselines.

Reliably identifying reinforced concrete defects (RCDs) plays a crucial role in assessing the structural integrity, traffic safety, and long-term durability of concrete bridges, which represent the most common bridge type worldwide. Nevertheless, available datasets for the recognition of RCDs are small in terms of size and class variety, which questions their usability in real-world scenarios and their role as a benchmark. Our contribution to this problem is "dacl10k", an exceptionally diverse RCD dataset for multi-label semantic segmentation comprising 9,920 images deriving from real-world bridge inspections. dacl10k distinguishes 12 damage classes as well as 6 bridge components that play a key role in the building assessment and recommending actions, such as restoration works, traffic load limitations or bridge closures. In addition, we examine baseline models for dacl10k which are subsequently evaluated. The best model achieves a mean intersection-over-union of 0.42 on the test set. dacl10k, along with our baselines, will be openly accessible to researchers and practitioners, representing the currently biggest dataset regarding number of images and class diversity for semantic segmentation in the bridge inspection domain.

Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of moment-text data which is hard to scale up because of the prohibitive annotation cost (fully-supervised), or unreliable when only the video-text pairwise relationships are available without fine-grained temporal annotations (weakly supervised). Recently, the vision-language models (VLM) demonstrate a new transfer learning paradigm to benefit different vision tasks through the universal visual-textual correlations derived from large-scale vision-language pairwise web data, which has also shown benefits to VMR by fine-tuning in the target domains. In this work, we propose a zero-shot method for adapting generalisable visual textual priors from arbitrary VLM to facilitate moment-text alignment, without the need for accessing the VMR data. To this end, we devise a conditional feature refinement module to generate boundary-aware visual features conditioned on text queries to enable better moment boundary understanding. Additionally, we design a bottom-up proposal generation strategy that mitigates the impact of domain discrepancies and breaks down complex-query retrieval tasks into individual action retrievals, thereby maximizing the benefits of VLM. Extensive experiments conducted on three VMR benchmark datasets demonstrate the notable performance advantages of our zero-shot algorithm, especially in the novel-word and novel-location out-of-distribution setups.

Modern building recognition methods, exemplified by the BRAILS framework, utilize supervised learning to extract information from satellite and street-view images for image classification and semantic segmentation tasks. However, each task module requires human-annotated data, hindering the scalability and robustness to regional variations and annotation imbalances. In response, we propose a new zero-shot workflow for building attribute extraction that utilizes large-scale vision and language models to mitigate reliance on external annotations. The proposed workflow contains two key components: image-level captioning and segment-level captioning for the building images based on the vocabularies pertinent to structural and civil engineering. These two components generate descriptive captions by computing feature representations of the image and the vocabularies, and facilitating a semantic match between the visual and textual representations. Consequently, our framework offers a promising avenue to enhance AI-driven captioning for building attribute extraction in the structural and civil engineering domains, ultimately reducing reliance on human annotations while bolstering performance and adaptability.

A crucial part of any home is the roof over our heads to protect us from the elements. In this paper we present the Zeitview Rooftop Geometry (ZRG) dataset for residential rooftop understanding. ZRG is a large-scale residential rooftop inspection dataset of over 20k properties from across the U.S. and includes high resolution aerial orthomosaics, digital surface models (DSM), colored point clouds, and 3D roof wireframe annotations. We provide an in-depth analysis and perform several experimental baselines including roof outline extraction, monocular height estimation, and planar roof structure extraction, to illustrate a few of the numerous applications unlocked by this dataset.

Generative Neural Radiance Fields (NeRFs) have demonstrated remarkable proficiency in synthesizing multi-view images by learning the distribution of a set of unposed images. Despite the aptitude of existing Generative NeRFs in generating 3D-consistent high-quality random samples within data distribution, the creation of a 3D representation of a singular input image remains a formidable challenge. In this manuscript, we introduce ZIGNeRF, an innovative model that executes zero-shot Generative Adversarial Network (GAN) inversion for the generation of multi-view images from a single out-of-distribution image. The model is underpinned by a novel inverter that maps out-of-domain images into the latent code of the generator manifold. Notably, ZIGNeRF is capable of disentangling the object from the background and executing 3D operations such as 360-degree rotation or depth and horizontal translation. The efficacy of our model is validated using multiple real-image datasets: Cats, AFHQ, CelebA, CelebA-HQ, and CompCars.

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot TAD methods showcase the promising openset setting by leveraging large-scale contrastive visuallanguage (ViL) pretrained models. However, existing zeroshot TAD methods have limitations on how to properly construct the strong relationship between two Interdependent tasks of localization and classification and adapt ViL model to video understanding. In this work, we present ZEETAD, featuring two modules: dual-localization and zeroshot proposal classification. The former is a Transformerbased module that detects action events while selectively collecting crucial semantic embeddings for later Recognition. The latter one, CLIP-based module, generates semantic embeddings from text and frame inputs for each temporal unit. Additionally, we enhance discriminative capability on unseen classes by minimally updating the frozen CLIP encoder with lightweight adapters. Extensive experiments on THUMOS14 and ActivityNet-1.3 datasets demonstrate our approach's superior performance in zero-shot TAD and effective knowledge transfer from ViL models to unseen action categories. Code is available at https: //github.com/UARK-AICV/ZEETAD.

While gait recognition has seen many advances in recent years, the occlusion problem has largely been ignored. This problem is especially important for gait recognition from uncontrolled outdoor sequences at range - since any small obstruction can affect the recognition system. Most current methods assume the availability of complete body information while extracting the gait features. When parts of the body are occluded, these methods may hallucinate and output a corrupted gait signature as they try to look for body parts which are not present in the input at all. To address this, we exploit the learned occlusion type while extracting identity features from videos. Thus, in this work, we propose an occlusion aware gait recognition method which can be used to model intrinsic occlusion awareness into potentially any state-of-the-art gait recognition method. Our experiments on the challenging GREW and BRIAR datasets show that networks enhanced with this occlusion awareness perform better at recognition tasks than their counterparts trained on similar occlusions.

Winograd-based convolution can reduce the total number of operations needed for convolutional neural network (CNN) inference on edge devices. Most edge hardware accelerators use low-precision, 8-bit integer arithmetic units to improve energy efficiency and latency. This makes CNN quantization a critical step before deploying the model on such an edge device. To extract the benefits of fast Winograd-based convolution and efficient integer quantization, the two approaches must be combined. Research has shown that the transform required to execute convolutions in the Winograd domain results in numerical instability and severe accuracy degradation when combined with quantization, making the two techniques incompatible on edge hardware. This paper proposes a novel training scheme to achieve efficient Winograd-accelerated, quantized CNNs. 8-bit quantization is applied to all the intermediate results of the Winograd convolution without sacrificing task-related accuracy. This is achieved by introducing clipping factors in the intermediate quantization stages as well as using the complex numerical system to improve the transform. We achieve 2.8x and 2.1x reduction in MAC operations on ResNet-20-CIFAR-10 and ResNet-18-ImageNet, respectively, with no accuracy degradation.

In this paper, we present WildlifeDatasets - an open-source toolkit intended primarily for ecologists and computer-vision / machine-learning researchers. The WildlifeDatasets is written in Python, allows straightforward access to publicly available wildlife datasets, and provides a wide variety of methods for dataset pre-processing, performance analysis, and model fine-tuning. We showcase the toolkit in various scenarios and baseline experiments, including, to the best of our knowledge, the most comprehensive experimental comparison of datasets and methods for wildlife re-identification, including both local descriptors and deep learning approaches. Furthermore, we provide the first-ever foundation model for individual re-identification within a wide range of species - MegaDescriptor - that provides state-of-the-art performance on animal re-identification datasets and outperforms other pre-trained models such as CLIP and DINOv2 by a significant margin. To make the model available to the general public and to allow easy integration with any existing wildlife monitoring applications, we provide multiple MegaDescriptor flavors (i.e., Small, Medium, and Large) through the HuggingFace hub.

Learning from bounding-boxes annotations has shown great potential in weakly-supervised 3D point cloud in- stance segmentation. However, we observed that existing methods would suffer severe performance degradation with perturbed bounding box annotations. To tackle this is- sue, we propose a complementary image prompt-induced weakly-supervised point cloud instance segmentation (CIP- WPIS) method. CIP-WPIS leverages pretrained knowledge embedded in the 2D foundation model SAM and 3D geo- metric prior to achieve accurate point-wise instance labels from the bounding box annotations. Specifically, CIP-WPIS first selects image views in which 3D candidate points of an instance are fully visible. Then, we generate complemen- tary background and foreground prompts from projections to obtain SAM 2D instance mask predictions. According to these, we assign the confidence values to points indicating the likelihood of points belonging to the instance. Furthermore, we utilize 3D geometric homogeneity provided by superpoints to decide the final instance label assignments. In this fashion, we achieve high-quality 3D point-wise in- stance labels. Extensive experiments on both Scannet-v2 and S3DIS benchmarks proves that our method not only achieves state-of-the-art performance for bounding-boxes supervised point cloud instance segmentation, but also exhibits robustness against noisy 3D bounding-box annotations.

Generic Event Boundary Detection (GEBD) task aims to recognize generic, taxonomy-free boundaries that segment a video into meaningful events. Current methods typically involve a neural model trained on a large volume of data, demanding substantial computational power and storage space. We explore two pivotal questions pertaining to GEBD: Can non-parametric algorithms outperform unsupervised neural methods? Does motion information alone suffice for high performance? This inquiry drives us to algorithmically harness motion cues for identifying generic event boundaries in videos. In this work, we propose FlowGEBD, a non-parametric, unsupervised technique for GEBD. Our approach entails two algorithms utilizing optical flow: (i) Pixel Tracking and (ii) Flow Normalization. By conducting thorough experimentation on the challenging Kinetics-GEBD and TAPOS datasets, our results establish FlowGEBD as the new state-of-the-art (SOTA) among unsupervised methods. FlowGEBD exceeds the neural models on the Kinetics-GEBD dataset by obtaining an F1@0.05 score of 0.713 with an absolute gain of 31.7% compared to the unsupervised baseline and achieves an average F1 score of 0.623 on the TAPOS validation dataset.

Semantic segmentation represents a fundamental task in computer vision with various application areas such as autonomous driving, medical imaging, or remote sensing. For evaluating and comparing semantic segmentation models, the mean intersection over union (mIoU) is currently the gold standard. However, while mIoU serves as a valuable benchmark, it does not offer insights into the types of errors incurred by a model. Moreover, different types of errors may have different impacts on downstream applications. To address this issue, we propose an intuitive method for the systematic categorization of errors, thereby enabling a fine-grained analysis of semantic segmentation models. Since we assign each erroneous pixel to precisely one error type, our method seamlessly extends the popular IoU-based evaluation by shedding more light on the false positive and false negative predictions. Our approach is model- and dataset-agnostic, as it does not rely on additional information besides the predicted and ground-truth segmentation masks. In our experiments, we demonstrate that our method accurately assesses model strengths and weaknesses on a quantitative basis, thus reducing the dependence on time-consuming qualitative model inspection. We analyze a variety of state-of-the-art semantic segmentation models, revealing systematic differences across various architectural paradigms. Exploiting the gained insights, we showcase that combining two models with complementary strengths in a straightforward way is sufficient to consistently improve mIoU, even for models setting the current state of the art on ADE20K. We release a toolkit for our evaluation method at https://github.com/mxbh/beyond-iou.

Recently, inversion methods have been exploring the incorporation of additional high-rate information from pretrained generators (such as weights or intermediate features) to improve the refinement of inversion and editing results from embedded latent codes. While such techniques have shown reasonable improvements in reconstruction, they often lead to a decrease in editing capability, especially when dealing with complex images that contain occlusions, detailed backgrounds, and artifacts. A vital crux is refining inversion results, avoiding editing capability degradation. To address this problem, we propose a novel refinement mechanism called Domain-Specific Hybrid Refinement (DHR), which draws on the advantages and disadvantages of two mainstream refinement techniques. We find that the weight modulation can gain favorable editing results but is vulnerable to these complex image areas and feature modulation is efficient at reconstructing. Hence, we divide the image into two domains and process them with these two methods separately. We first propose a Domain-Specific Segmentation module to automatically segment images into in-domain and out-of-domain parts according to their invertibility and editability without additional data annotation, where our hybrid refinement process aims to maintain the editing capability for in-domain areas and improve fidelity for both of them. We achieve this through Hybrid Modulation Refinement, which respectively refines these two domains by weight modulation and feature modulation. Our proposed method is compatible with all latent code embedding methods. Extension experiments demonstrate that our approach achieves state-of-the-art in real image inversion and editing. Code is available at https://github.com/caopulan/Domain-Specific_Hybrid_Refinement_Inversion.

Many tasks in video analysis and understanding boil down to the need for frame-based feature learning, aiming to encapsulate the relevant visual content so as to enable simpler and easier subsequent processing. While supervised strategies for this learning task can be envisioned, self and weakly-supervised alternatives are preferred due to the difficulties in getting labeled data. This paper introduces LRProp -- a novel weakly-supervised representation learning approach, with an emphasis on the application of temporal alignment between pairs of videos of the same action category. The proposed approach uses a transformer encoder for extracting frame-level features, and employs the DTW algorithm within the training iterations in order to identify the alignment path between video pairs. Through a process referred to as "pair-wise position propagation", the probability distributions of these correspondences per location are matched with the similarity of the frame-level features via KL-divergence minimization. The proposed algorithm uses also a regularized SoftDTW loss for better tuning the learned features. Our novel representation learning paradigm consistently outperforms the state of the art on temporal alignment tasks, establishing a new performance bar over several downstream video analysis applications.

The remarkable generative capabilities of denoising diffusion models have raised new concerns regarding the authenticity of the images we see every day on the Internet. However, the vast majority of existing deepfake detection models are tested against previous generative approaches (e.g. GAN) and usually provide only a "fake" or "real" label per image. We believe a more informative output would be to augment the per-image label with a localization map indicating which regions of the input have been manipulated. To this end, we frame this task as a weakly-supervised localization problem and identify three main categories of methods (based on either explanations, local scores or attention), which we compare on an equal footing by using the Xception network as the common backbone architecture. We provide a careful analysis of all the main factors that parameterize the design space: choice of method, type of supervision, dataset and generator used in the creation of manipulated images; our study is enabled by constructing datasets in which only one of the components is varied. Our results show that weakly-supervised localization is attainable, with the best performing detection method (based on local scores) being less sensitive to the looser supervision than to the mismatch in terms of dataset or generator.

Image super-resolution research recently has been dominated by transformer models which need higher computational resources than CNNs due to the quadratic complexity of self-attention. We propose a new neural network -- WaveMixSR -- for image super-resolution based on the WaveMix architecture which uses a 2D-discrete wavelet transform for spatial token-mixing. Unlike transformer-based models, WaveMixSR does not unroll the image as a sequence of pixels/patches. It uses the inductive bias of convolutions along with the lossless token-mixing property of wavelet transform to achieve higher performance while requiring fewer resources and training data. We compare the performance of our network with other state-of-the-art methods for image super-resolution. Our experiments show that WaveMixSR achieves competitive performance in all datasets and reaches state-of-the-art performance in the BSD100 dataset on multiple super-resolution tasks. Our model is able to achieve this performance using less training data and computational resources while maintaining high parameter efficiency compared to current state-of-the-art models.

Gait Recognition is a computer vision task aiming to identify people by their walking patterns. Although existing methods often show high performance on specific datasets, they lack the ability to generalize to unseen scenarios. Unsupervised Domain Adaptation (UDA) tries to adapt a model, pre-trained in a supervised manner on a source domain, to an unlabelled target domain. There are only a few works on UDA for gait recognition proposing solutions to limited scenarios. In this paper, we reveal a fundamental phenomenon in adaptation of gait recognition models, caused by the bias in the target domain to viewing angle or walking direction. We then suggest a remedy to reduce this bias with a novel triplet selection strategy combined with curriculum learning. To this end, we present Gait Orientation-based method for Unsupervised Domain Adaptation (GOUDA). We provide extensive experiments on four widely-used gait datasets, CASIA-B, OU-MVLP, GREW, and Gait3D, and on three backbones, GaitSet, GaitPart, and GaitGL, justifying the view bias and showing the superiority of our proposed method over prior UDA works.

Point clouds are often sparse and incomplete in real-world scenarios. The prevailing methods for point cloud completion typically rely on encoding the partial points and then decoding complete points from a global feature vector, which might lose the existing patterns and elaborate structures. To address these issues, we propose WalkFormer, a novel approach to predict complete point clouds through a partial deformation process. Concretely, our method samples locally dominant points based on feature similarity and moves the points to form the missing part. Since these points maintain representative information of the surrounding structures, they are appropriately selected as the starting points for multiple guided walks. Furthermore, we design a Route Transformer module to exploit and aggregate the walk information with topological relations. These guided walks facilitate the learning of long-range dependencies for predicting shape deformation. Qualitative and quantitative evaluations demonstrate that our proposed approach achieves superior performance compared to state-of-the-art methods in the 3D point cloud completion task.