ECCV 2022 Papers

"Can we relocalize in a scene represented by a single reference image? Standard visual relocalization requires hundreds of images and scale calibration to build a scene-specific 3D map. In contrast, we propose Map-free Relocalization, i.e., using only one photo of a scene to enable instant, metric scaled relocalization. Existing datasets are not suitable to benchmark map-free relocalization, due to their focus on large scenes or their limited variability. Thus, we have constructed a new dataset of 655 small places of interest, such as sculptures, murals and fountains, collected worldwide. Each place comes with a reference image to serve as a relocalization anchor, and dozens of query images with known, metric camera poses. The dataset features changing conditions, stark viewpoint changes, high variability across places, and queries with low to no visual overlap with the reference image.We identify two viable families of existing methods to provide baseline results: relative pose regression, and feature matching combined with single-image depth prediction. While these methods show reasonable performance on some favorable scenes in our dataset, map-free relocalization proves to be a challenge that requires new, innovative solutions."

"Deep neural networks (DNNs) for point clouds have achieved superior performance on a range of 3D vision tasks. However, generalization to out-of-distribution 3D point clouds remains challenging for DNNs. Due to the expensive cost or even infeasibility of annotating large-scale point clouds, it is critical but yet has not been fully explored to design methods to generalize DNN models to unseen domains of point clouds without any access to them during the training process. In this paper, we propose to learn 3D point cloud representation on a seen source domain and generalize to an unseen target domain via adversarial learning. Specifically, we unify several geometric transformations in a manifold-based framework under which distance between transformations is well-defined. Measured by the distance, adversarial samples are mined to form intermediate domains and retained in an adaptive replay-based memory. We further provide theoretical justification for the intermediate domains to reduce the generalization error of the DNN models. Experimental results on synthetic-to-real datasets illustrate that our method outperforms existing 3D deep learning models for domain generalization."

"Most image-to-image translation methods require a large number of training images, which restricts their applicability. We instead propose ManiFest: a framework for few-shot image translation that learns a context-aware representation of a target domain from a few images only. To enforce feature consistency, our framework learns a style manifold between source and additional anchor domains (assumed to be composed of large numbers of images). The learned manifold is interpolated and deformed towards the few-shot target domain via patch-based adversarial and feature statistics alignment losses. All of these components are trained simultaneously during a single end-to-end loop. In addition to the general few-shot translation task, our approach can alternatively be conditioned on a single exemplar image to reproduce its specific style. Extensive experiments demonstrate the efficacy of ManiFest on multiple tasks, outperforming the state-of-the-art on all metrics. Our code is avaliable at https://github.com/cv-rits/ManiFest."

"Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses additional challenges in vision-language modelling compared to the general domain, and previous work has used insufficiently adapted models that lack domain-specific language understanding. In this paper, we show that principled textual semantic modelling can substantially improve contrastive learning in self-supervised vision-language processing. We release a language model that achieves state-of-the-art results in radiology natural-language inference through its improved vocabulary and novel language pretraining objective leveraging semantics and discourse characteristics in radiology reports. Further, we propose a self-supervised joint vision-language approach with a focus on better text modelling. It establishes new state of the art results on a wide range of publicly available benchmarks, in part by leveraging our new domain-specific language model. We release a new dataset with locally-aligned phrase grounding annotations by radiologists to facilitate the study of complex semantic modelling in biomedical vision-language processing. A broad evaluation, including on this new dataset, shows that our contrastive learning approach, aided by textual-semantic modelling, outperforms prior methods in segmentation tasks, despite only using a global-alignment objective."

"A visual counterfactual explanation replaces image regions in a query image with regions from a distractor image such that the system’s decision on the transformed image changes to the distractor class. In this work, we present a novel framework for computing visual counterfactual explanations based on two key ideas. First, we enforce that the replaced and replacer regions contain the same semantic part, resulting in more semantically consistent explanations. Second, we use multiple distractor images in a computationally efficient way and obtain more discriminative explanations with fewer region replacements. Our approach is 27 % more semantically consistent and an order of magnitude faster than a competing method on three fine-grained image recognition datasets. We highlight the utility of our counterfactuals over existing works through machine teaching experiments where we teach humans to classify different bird species. We also complement our explanations with the vocabulary of parts and attributes that contributed the most to the system’s decision. In this task as well, we obtain state-of-the-art results when using our counterfactual explanations relative to existing works, reinforcing the importance of semantically consistent explanations. Source code is available at https://github.com/facebookresearch/visual-counterfactuals."

"Recent text-to-image generation methods provide a simple yet exciting conversion capability between text and image domains. While these methods have incrementally improved the generated image fidelity and text relevancy, several pivotal gaps remain unanswered, limiting applicability and quality. We propose a novel text-to-image method that addresses these gaps by (i) enabling a simple control mechanism complementary to text in the form of a scene, (ii) introducing elements that substantially improve the tokenization process by employing domain-specific knowledge over key image regions (faces and salient objects), and (iii) adapting classifier-free guidance for the transformer use case. Our model achieves state-of-the-art FID and human evaluation results, unlocking the ability to generate high fidelity images in a resolution of 512×512 pixels, significantly improving visual quality. Through scene controllability, we introduce several new capabilities: (i) Scene editing, (ii) text editing with anchor scenes, (iii) overcoming out-of-distribution text prompts, and (iv) story illustration generation, as demonstrated in \href{https://youtu.be/N4BagnXzPXY}{the story we wrote}."

"We present MaCLR, a novel method to explicitly perform cross-modal self-supervised video representations learning from visual and motion modalities. Compared to previous video representation learn- ing methods that mostly focus on learning motion cues implicitly from RGB inputs, MaCLR enriches standard contrastive learning objectives for RGB video clips with a cross-modal learning objective between a Motion pathway and a Visual pathway. We show that the representation learned with our MaCLR method focuses more on foreground motion re- gions and thus generalizes better to downstream tasks. To demonstrate this, we evaluate MaCLR on five datasets for both action recognition and action detection, and demonstrate state-of-the-art self-supervised perfor- mance on all datasets. Furthermore, we show that MaCLR representa- tion can be as effective as representations learned with full supervision on UCF101 and HMDB51 action recognition, and even outperform the supervised representation for action recognition on VidSitu and SSv2, and action detection on AVA."

"RGB-D salient object detection (SOD) enjoys significant advantages in understanding 3D geometry of the scene. However, the geometry information conveyed by depth maps are mostly under-explored in existing RGB-D SOD methods. In this paper, we propose a new framework to address this issue. We augment the input image with multiple different views rendered using the depth maps, and cast the conventional single-view RGB-D SOD into a multi-view setting. Since different views captures complementary context of the 3D scene, the accuracy can be significantly improved through multi-view aggregation. We further design a multi-view saliency detection network (MVSalNet), which firstly performs saliency prediction for each view separately and incorporates multi-view outputs through a fusion model to produce final saliency prediction. A dynamic filtering module is also designed to facilitate more effective and flexible feature extraction. Extensive experiments on 6 widely used datasets demonstrate that our approach compares favorably against state-of-the-art approaches."

"Learning-based Multi-View Stereo (MVS) methods warp source images into the reference camera frustum to form 3D volumes, which are fused as a cost volume to be regularized by subsequent networks. The fusing step plays a vital role in bridging 2D semantics and 3D spatial associations. However, previous methods utilize extra networks to learn 2D information as fusing cues, underusing 3D spatial correlations and bringing additional computation costs. Therefore, we present MVSTER, which leverages the proposed epipolar Transformer to learn both 2D semantics and 3D spatial associations efficiently. Specifically, the epipolar Transformer utilizes a detachable monocular depth estimator to enhance 2D semantics and uses cross-attention to construct data-dependent 3D associations along epipolar line. Additionally, MVSTER is built in a cascade structure, where entropy-regularized optimal transport is leveraged to propagate finer depth estimations in each stage. Extensive experiments show MVSTER achieves state-of-the-art reconstruction performance with significantly higher efficiency: Compared with MVSNet and CasMVSNet, our MVSTER achieves 34% and 14% relative improvements on the DTU benchmark, with 80% and 51% relative reductions in running time. MVSTER also ranks first on Tanks&Temples-Advanced among all published works. Code is available at https://github.com/JeffWang987/MVSTER."

"Recently, masked image modeling (MIM) has become a promising direction for visual pre-training. In the context of vision transformers, MIM learns effective visual representation by aligning the token-level features with a pre-defined space (e,g,, BEIT used a d-VAE trained on a large image corpus as the tokenizer). In this paper, we go one step further by introducing guidance from other modalities and validating that such additional knowledge leads to impressive gains for visual pre-training. The proposed approach is named Multimodality-guided Visual Pre-training (MVP), in which we replace the tokenizer with the vision branch of CLIP, a vision-language model pre-trained on 400 million image-text pairs. We demonstrate the effectivenss of MVP by performing standard experiments, i.e., pre-training the ViT models on ImageNet and fine-tuning them on a series of downstream visual recognition tasks. In particular, pre-training ViT-Base/16 for 300 epochs, MVP reports a 52.4% mIOU on ADE-20K, surpassing BEIT (the baseline and previous state-of-the-art) with an impressive margin of 6.8%."

"Aiming to generalize the model trained in source domains to unseen target domains, domain generalization (DG) has attracted lots of attention recently. Since target domains can not be involved in training, overfitting to source domains is inevitable. As a popular regularization technique, the meta-learning training scheme has shown its ability to resist overfitting. However, in the training stage, current meta-learning-based methods utilize only one task along a single optimization trajectory, which might produce biased and noisy optimization direction. Beyond the training stage, overfitting could also cause unstable prediction in the test stage. In this paper, we propose a novel multi-view DG framework to effectively reduce the overfitting in both the training and test stage. Specifically, in the training stage, we develop a multi-view regularized meta-learning algorithm that employs multiple optimization trajectories to produce a suitable optimization direction for model updating. We also theoretically show the generalization bound could be reduced by increasing the number of tasks in each trajectory. In the test stage, to alleviate unstable prediction, we utilize multiple augmented images to yield a multi-view prediction, which significantly promotes model reliability. Extensive experiments on three benchmark datasets validate that our method can find a flat minimum to enhance generalization and outperform several state-of-the-art approaches."

"Multimodal video-audio-text understanding and generation can benefit from datasets that are narrow but rich. The narrowness allows bite-sized challenges that the research community can make progress on. The richness ensures we are making progress along the core challenges. To this end, we present a large-scale video-audio-text dataset MUGEN, collected using the open-sourced platform game CoinRun. We made substantial modifications to make the game richer by introducing audio and enabling new interactions. We trained RL agents with different objectives to navigate the game and interact with 13 objects and characters. This allows us to automatically extract a large collection of diverse videos and associated audio. We sample 375K video clips (3.2s each) and collect text descriptions from human annotators. Each video has additional annotations that are extracted automatically from the game engine, such as accurate semantic maps for each frame and templated textual descriptions. Altogether, MUGEN can help progress research in many tasks in multimodal understanding and generation. We benchmark representative approaches on tasks involving video-audio-text retrieval and generation. Our dataset and code are released at: https://mugen-org.github.io/."

"Recently, DEtection TRansformer (DETR), an end-to-end object detection pipeline, has achieved promising performance. However, it requires large-scale labeled data and suffers from domain shift, especially when no labeled data is available in the target domain. To solve this problem, we propose an end-to-end cross-domain detection Transformer based on the mean teacher framework, MTTrans, which can fully exploit unlabeled target domain data in object detection training and transfer knowledge between domains via pseudo labels. We further propose the comprehensive multi-level feature alignment to improve the pseudo labels generated by the mean teacher framework taking advantage of the cross-scale self-attention mechanism in Deformable DETR. Image and object features are aligned at the local, global, and instance levels with domain query-based feature alignment (DQFA), bi-level graph-based prototype alignment (BGPA), and token-wise image feature alignment (TIFA). On the other hand, the unlabeled target domain data pseudo-labeled and available for the object detection training by the mean teacher framework can lead to better feature extraction and alignment. Thus, the mean teacher framework and the comprehensive multi-level feature alignment can be optimized iteratively and mutually based on the architecture of Transformers. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance in three domain adaptation scenarios, especially the result of Sim10k to Cityscapes scenario is remarkably improved from 52.6 mAP to 57.9 mAP. Code will be released."

"In this paper, we explore the advantages of utilizing transformer structures for addressing multi-task learning (MTL). Specifically, we demonstrate that models with transformer structures are more appropriate for MTL than convolutional neural networks (CNNs), and we propose a novel transformer-based architecture named MTFormer for MTL. In the framework, multiple tasks share the same transformer encoder and transformer decoder, and lightweight branches are introduced to harvest task-specific outputs, which increases the MTL performance and reduces the time-space complexity. Furthermore, information from different task domains can benefit each other, and we conduct cross-task reasoning. We propose a cross-task attention mechanism for further boosting the MTL results. The cross-task attention mechanism brings little parameters and computations while introducing extra performance improvements. Besides, we design a self-supervised cross-task contrastive learning algorithm for further boosting the MTL performance. Extensive experiments are conducted on two multi-task learning datasets, on which MTFormer achieves state-of-the-art results with limited network parameters and computations. It also demonstrates significant superiorities for few-shot learning and zero-shot learning."

"Accurate and reliable 3D detection is vital for many applications including autonomous driving vehicles and service robots. In this paper, we present a flexible and high-performance 3D detection frame-work, named MPPNet, for 3D temporal object detection with point cloud sequences. We propose a novel three-hierarchy framework with proxy points for multi-frame feature encoding and interactions to achieve better detection. The three hierarchies conduct per-frame feature encoding, short-clip feature fusion, and whole-sequence feature aggregation, respectively. To enable processing long-sequence point clouds with reasonable computational resources, intra-group feature mixing and inter-group feature attention are proposed to form the second and third feature encoding hierarchies, which are recurrently applied for aggregating multi-frame trajectory features. The proxy points not only act as consistent object representations for each frame, but also serves as the courier to facilitate feature interaction between frames. The experiments on large Waymo Open dataset show that our approach outperforms state-of-the-art methods with large margins when applied to both short (e.g., 4-frame) and long (e.g., 16-frame) point cloud sequences. Code will be publicly available at https://github.com/open-mmlab/OpenPCDet."

"Partial occlusion effects are a phenomenon that blurry objects near a camera are semi-transparent, resulting in partial appearance of occluded background. However, it is challenging for existing bokeh rendering methods to simulate realistic partial occlusion effects due to the missing information of the occluded area in an all-in-focus image. Inspired by the learnable 3D scene representation, Multiplane Image (MPI), we attempt to address the partial occlusion by introducing a novel MPI-based high-resolution bokeh rendering framework, termed MPIB. To this end, we first present an analysis on how to apply the MPI representation to bokeh rendering. Based on this analysis, we propose an MPI representation module combined with a background inpainting module to implement high-resolution scene representation. This representation can then be reused to render various bokeh effects according to the controlling parameters. To train and test our model, we also design a ray-tracing-based bokeh generator for data generation. Extensive experiments on synthesized and real-world images validate the effectiveness and flexibility of this framework."

"Temporal modeling of objects is a key challenge in multiple-object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association prevents end-to-end exploitation of temporal variations in video sequence. In this paper, we propose MOTR, which extends DETR \cite{carion2020detr} and introduces “track query” to model the tracked instances in the entire video. Track query is transferred and updated frame-by-frame to perform iterative prediction over time. We propose tracklet-aware label assignment to train track queries and newborn object queries. We further propose temporal aggregation network and collective average loss to enhance temporal relation modeling. Experimental results on DanceTrack show that MOTR significantly outperforms state-of-the-art method, ByteTrack by 6.5\% on HOTA metric. On MOT17, MOTR outperforms our concurrent works, TrackFormer and TransTrack, on association performance. MOTR can serve as a stronger baseline for future research on temporal modeling and Transformer-based trackers. Code is available at \url{https://github.com/anonymous4669/MOTR}."

"There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison of datasets, and reduces the conversation on tracker performance to a matter of leader board position. As a remedy, we present the novel MOT dataset complexity metric (MOTCOM), which is a combination of three sub-metrics inspired by key problems in MOT: occlusion, erratic motion, and visual similarity. The insights of MOTCOM can open nuanced discussions on tracker performance and may lead to a wider acknowledgement of novel contributions developed for either less known datasets or those aimed at solving sub-problems. We evaluate MOTCOM on the comprehensive MOT17, MOT20, and MOTSynth datasets and show that MOTCOM is far better at describing the complexity of MOT sequences compared to the conventional density and number of tracks. Project page at https://vap.aau.dk/motcom."

"3D dense captioning is a recently-proposed novel task, where point clouds contain more geometric information than the 2D counterpart. However, it is also more challenging due to the higher complexity and wider variety of inter-object relations contained in point clouds. Existing methods only treat such relations as by-products of object feature learning in graphs without specifically encoding them, which leads to sub-optimal results. In this paper, aiming at improving 3D dense captioning via capturing and utilizing the complex relations in the 3D scene, we propose MORE, a Multi-Order RElation mining model, to support generating more descriptive and comprehensive captions. Technically, our MORE encodes object relations in a progressive manner since complex relations can be deduced from a limited number of basic ones. We first devise a novel Spatial Layout Graph Convolution (SLGC), which semantically encodes several first-order relations as edges of a graph constructed over 3D object proposals. Next, from the resulting graph, we further extract multiple triplets which encapsulate basic first-order relations as the basic unit, and construct several Object-centric Triplet Attention Graphs (OTAG) to infer multi-order relations for every target object. The updated node features from OTAG are aggregated and fed into the caption decoder to provide abundant relational cues, so that captions including diverse relations with context objects can be generated. Extensive experiments on the Scan2Cap dataset prove the effectiveness of our proposed MORE and its components, and we also outperform the current state-of-the-art method. Our code is available at https://github.com/SxJyJay/MORE."