Laura Leal-Taixé

Niket Agarwal, Arslan Ali, Maciej Bala et al. · nvidia

Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make Cosmos open-source and our models open-weight with permissive licenses available via https://github.com/nvidia-cosmos/cosmos-predict1.

Yang Liu, Shen Yan, Laura Leal-Taixé et al. · deepmind, gatech

Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. The dominant form of data augmentation applies invariant transforms, where the learning target of a sample is invariant to the transform applied to that sample. We draw inspiration from human visual classification studies and propose generalizing augmentation with invariant transforms to soft augmentation where the learning target softens non-linearly as a function of the degree of the transform applied to the sample: e.g., more aggressive image crop augmentations produce less confident learning targets. We demonstrate that soft targets allow for more aggressive data augmentation, offer more robust performance boosts, work with other augmentation policies, and interestingly, produce better calibrated models (since they are trained to be less confident on aggressively cropped/occluded examples). Combined with existing aggressive augmentation strategies, soft target 1) doubles the top-1 accuracy boost across Cifar-10, Cifar-100, ImageNet-1K, and ImageNet-V2, 2) improves model occlusion performance by up to $4\times$, and 3) halves the expected calibration error (ECE). Finally, we show that soft augmentation generalizes to self-supervised classification tasks. Code available at https://github.com/youngleox/soft_augmentation

Jenny Seidenschwarz, Guillem Brasó, Victor Castro Serrano et al.

For a long time, the most common paradigm in Multi-Object Tracking was tracking-by-detection (TbD), where objects are first detected and then associated over video frames. For association, most models resourced to motion and appearance cues, e.g., re-identification networks. Recent approaches based on attention propose to learn the cues in a data-driven manner, showing impressive results. In this paper, we ask ourselves whether simple good old TbD methods are also capable of achieving the performance of end-to-end models. To this end, we propose two key ingredients that allow a standard re-identification network to excel at appearance-based tracking. We extensively analyse its failure cases, and show that a combination of our appearance features with a simple motion model leads to strong tracking results. Our tracker generalizes to four public datasets, namely MOT17, MOT20, BDD100k, and DanceTrack, achieving state-of-the-art performance. https://github.com/dvl-tum/GHOST.

Guillem Braso, Orcun Cetintas, Laura Leal-Taixe

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) and Multiple Object Tracking and Segmentation (MOTS) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such structured domain is not trivial. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and exploit contextual features. It then jointly predicts both final solutions for the data association problem and segmentation masks for all objects in the scene while exploiting synergies between the two tasks. We achieve state-of-the-art results for both tracking and segmentation in several publicly available datasets. Our code is available at github.com/ocetintas/MPNTrackSeg.

Patrick Dendorfer, Vladimir Yugay, Aljoša Ošep et al.

Recent developments in monocular multi-object tracking have been very successful in tracking visible objects and bridging short occlusion gaps, mainly relying on data-driven appearance models. While we have significantly advanced short-term tracking performance, bridging longer occlusion gaps remains elusive: state-of-the-art object trackers only bridge less than 10% of occlusions longer than three seconds. We suggest that the missing key is reasoning about future trajectories over a longer time horizon. Intuitively, the longer the occlusion gap, the larger the search space for possible associations. In this paper, we show that even a small yet diverse set of trajectory predictions for moving agents will significantly reduce this search space and thus improve long-term tracking robustness. Our experiments suggest that the crucial components of our approach are reasoning in a bird's-eye view space and generating a small yet diverse set of forecasts while accounting for their localization uncertainty. This way, we can advance state-of-the-art trackers on the MOTChallenge dataset and significantly improve their long-term tracking performance. This paper's source code and experimental data are available at https://github.com/dendorferpatrick/QuoVadis.

Aysim Toker, Lukas Kondmann, Mark Weber et al.

Earth observation is a fundamental tool for monitoring the evolution of land use in specific areas of interest. Observing and precisely defining change, in this context, requires both time-series data and pixel-wise segmentations. To that end, we propose the DynamicEarthNet dataset that consists of daily, multi-spectral satellite observations of 75 selected areas of interest distributed over the globe with imagery from Planet Labs. These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes. DynamicEarthNet is the first dataset that provides this unique combination of daily measurements and high-quality labels. In our experiments, we compare several established baselines that either utilize the daily observations as additional training data (semi-supervised learning) or multiple observations at once (spatio-temporal learning) as a point of reference for future research. Finally, we propose a new evaluation metric SCS that addresses the specific challenges associated with time-series semantic change segmentation. The data is available at: https://mediatum.ub.tum.de/1650201.

Marvin Eisenberger, Aysim Toker, Laura Leal-Taixé et al.

The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields. One major reason is its ease of integration into deep learning frameworks. To allow for an efficient training of respective neural networks, we propose an algorithm that obtains analytical gradients of a Sinkhorn layer via implicit differentiation. In comparison to prior work, our framework is based on the most general formulation of the Sinkhorn operator. It allows for any type of loss function, while both the target capacities and cost matrices are differentiated jointly. We further construct error bounds of the resulting algorithm for approximate inputs. Finally, we demonstrate that for a number of applications, simply replacing automatic differentiation with our algorithm directly improves the stability and accuracy of the obtained gradients. Moreover, we show that it is computationally more efficient, particularly when resources like GPU memory are scarce.

Luca Scofano, Alessio Sampieri, Elisabeth Schiele et al.

Scene-aware global human motion forecasting is critical for manifold applications, including virtual reality, robotics, and sports. The task combines human trajectory and pose forecasting within the provided scene context, which represents a significant challenge. So far, only Mao et al. NeurIPS'22 have addressed scene-aware global motion, cascading the prediction of future scene contact points and the global motion estimation. They perform the latter as the end-to-end forecasting of future trajectories and poses. However, end-to-end contrasts with the coarse-to-fine nature of the task and it results in lower performance, as we demonstrate here empirically. We propose a STAGed contact-aware global human motion forecasting STAG, a novel three-stage pipeline for predicting global human motion in a 3D environment. We first consider the scene and the respective human interaction as contact points. Secondly, we model the human trajectory forecasting within the scene, predicting the coarse motion of the human body as a whole. The third and last stage matches a plausible fine human joint motion to complement the trajectory considering the estimated contacts. Compared to the state-of-the-art (SoA), STAG achieves a 1.8% and 16.2% overall improvement in pose and trajectory prediction, respectively, on the scene-aware GTA-IM dataset. A comprehensive ablation study confirms the advantages of staged modeling over end-to-end approaches. Furthermore, we establish the significance of a newly proposed temporal counter called the "time-to-go", which tells how long it is before reaching scene contact and endpoints. Notably, STAG showcases its ability to generalize to datasets lacking a scene and achieves a new state-of-the-art performance on CMU-Mocap, without leveraging any social cues. Our code is released at: https://github.com/L-Scofano/STAG

Linyan Yang, Lukas Hoyer, Mark Weber et al.

Unsupervised Domain Adaptation (UDA) is the task of bridging the domain gap between a labeled source domain, e.g., synthetic data, and an unlabeled target domain. We observe that current UDA methods show inferior results on fine structures and tend to oversegment objects with ambiguous appearance. To address these shortcomings, we propose to leverage geometric information, i.e., depth predictions, as depth discontinuities often coincide with segmentation boundaries. We show that naively incorporating depth into current UDA methods does not fully exploit the potential of this complementary information. To this end, we present MICDrop, which learns a joint feature representation by masking image encoder features while inversely masking depth encoder features. With this simple yet effective complementary masking strategy, we enforce the use of both modalities when learning the joint feature representation. To aid this process, we propose a feature fusion module to improve both global as well as local information sharing while being robust to errors in the depth predictions. We show that our method can be plugged into various recent UDA methods and consistently improve results across standard UDA benchmarks, obtaining new state-of-the-art performances.

Vladimir Fomenko, Ismail Elezi, Deva Ramanan et al.

We tackle the problem of novel class discovery and localization (NCDL). In this setting, we assume a source dataset with supervision for only some object classes. Instances of other classes need to be discovered, classified, and localized automatically based on visual similarity without any human supervision. To tackle NCDL, we propose a two-stage object detection network Region-based NCDL (RNCDL) that uses a region proposal network to localize regions of interest (RoIs). We then train our network to learn to classify each RoI, either as one of the known classes, seen in the source dataset, or one of the novel classes, with a long-tail distribution constraint on the class assignments, reflecting the natural frequency of classes in the real world. By training our detection network with this objective in an end-to-end manner, it learns to classify all region proposals for a large variety of classes, including those not part of the labeled object class vocabulary. Our experiments conducted using COCO and LVIS datasets reveal that our method is significantly more effective than multi-stage pipelines that rely on traditional clustering algorithms. Furthermore, we demonstrate the generality of our approach by applying our method to a large-scale Visual Genome dataset, where our network successfully learns to detect various semantic classes without direct supervision.

Marvin Eisenberger, Aysim Toker, Laura Leal-Taixé et al.

We present G-MSM (Graph-based Multi-Shape Matching), a novel unsupervised learning approach for non-rigid shape correspondence. Rather than treating a collection of input poses as an unordered set of samples, we explicitly model the underlying shape data manifold. To this end, we propose an adaptive multi-shape matching architecture that constructs an affinity graph on a given set of training shapes in a self-supervised manner. The key idea is to combine putative, pairwise correspondences by propagating maps along shortest paths in the underlying shape graph. During training, we enforce cycle-consistency between such optimal paths and the pairwise matches which enables our model to learn topology-aware shape priors. We explore different classes of shape graphs and recover specific settings, like template-based matching (star graph) or learnable ranking/sorting (TSP graph), as special cases in our framework. Finally, we demonstrate state-of-the-art performance on several recent shape correspondence benchmarks, including real-world 3D scan meshes with topological noise and challenging inter-class pairs.

Mariia Gladkova, Nikita Korobov, Nikolaus Demmel et al.

Direct methods have shown excellent performance in the applications of visual odometry and SLAM. In this work we propose to leverage their effectiveness for the task of 3D multi-object tracking. To this end, we propose DirectTracker, a framework that effectively combines direct image alignment for the short-term tracking and sliding-window photometric bundle adjustment for 3D object detection. Object proposals are estimated based on the sparse sliding-window pointcloud and further refined using an optimization-based cost function that carefully combines 3D and 2D cues to ensure consistency in image and world space. We propose to evaluate 3D tracking using the recently introduced higher-order tracking accuracy (HOTA) metric and the generalized intersection over union similarity measure to mitigate the limitations of the conventional use of intersection over union for the evaluation of vision-based trackers. We perform evaluation on the KITTI Tracking benchmark for the Car class and show competitive performance in tracking objects both in 2D and 3D.

Qunjie Zhou, Sérgio Agostinho, Aljosa Osep et al.

In this paper, we propose to go beyond the well-established approach to vision-based localization that relies on visual descriptor matching between a query image and a 3D point cloud. While matching keypoints via visual descriptors makes localization highly accurate, it has significant storage demands, raises privacy concerns and requires update to the descriptors in the long-term. To elegantly address those practical challenges for large-scale localization, we present GoMatch, an alternative to visual-based matching that solely relies on geometric information for matching image keypoints to maps, represented as sets of bearing vectors. Our novel bearing vectors representation of 3D points, significantly relieves the cross-modal challenge in geometric-based matching that prevented prior work to tackle localization in a realistic environment. With additional careful architecture design, GoMatch improves over prior geometric-based matching work with a reduction of (10.67m,95.7deg) and (1.43m, 34.7deg) in average median pose errors on Cambridge Landmarks and 7-Scenes, while requiring as little as 1.5/1.7% of storage capacity in comparison to the best visual-based matching methods. This confirms its potential and feasibility for real-world localization and opens the door to future efforts in advancing city-scale visual localization methods that do not require storing visual descriptors.

Abhinav Agarwalla, Xuhua Huang, Jason Ziglar et al.

State-of-the-art lidar panoptic segmentation (LPS) methods follow bottom-up segmentation-centric fashion wherein they build upon semantic segmentation networks by utilizing clustering to obtain object instances. In this paper, we re-think this approach and propose a surprisingly simple yet effective detection-centric network for both LPS and tracking. Our network is modular by design and optimized for all aspects of both the panoptic segmentation and tracking task. One of the core components of our network is the object instance detection branch, which we train using point-level (modal) annotations, as available in segmentation-centric datasets. In the absence of amodal (cuboid) annotations, we regress modal centroids and object extent using trajectory-level supervision that provides information about object size, which cannot be inferred from single scans due to occlusions and the sparse nature of the lidar data. We obtain fine-grained instance segments by learning to associate lidar points with detected centroids. We evaluate our method on several 3D/4D LPS benchmarks and observe that our model establishes a new state-of-the-art among open-sourced models, outperforming recent query-based models.

Peter Kocsis, Peter Súkeník, Guillem Brasó et al.

Convolutional neural networks were the standard for solving many computer vision tasks until recently, when Transformers of MLP-based architectures have started to show competitive performance. These architectures typically have a vast number of weights and need to be trained on massive datasets; hence, they are not suitable for their use in low-data regimes. In this work, we propose a simple yet effective framework to improve generalization from small amounts of data. We augment modern CNNs with fully-connected (FC) layers and show the massive impact this architectural change has in low-data regimes. We further present an online joint knowledge-distillation method to utilize the extra FC layers at train time but avoid them during test time. This allows us to improve the generalization of a CNN-based model without any increase in the number of weights at test time. We perform classification experiments for a large range of network backbones and several standard datasets on supervised learning and active learning. Our experiments significantly outperform the networks without fully-connected layers, reaching a relative improvement of up to $16\%$ validation accuracy in the supervised setting without adding any extra parameters during inference.

Manuel Kolmet, Qunjie Zhou, Aljosa Osep et al.

Natural language-based communication with mobile devices and home appliances is becoming increasingly popular and has the potential to become natural for communicating with mobile robots in the future. Towards this goal, we investigate cross-modal text-to-point-cloud localization that will allow us to specify, for example, a vehicle pick-up or goods delivery location. In particular, we propose Text2Pos, a cross-modal localization module that learns to align textual descriptions with localization cues in a coarse- to-fine manner. Given a point cloud of the environment, Text2Pos locates a position that is specified via a natural language-based description of the immediate surroundings. To train Text2Pos and study its performance, we construct KITTI360Pose, the first dataset for this task based on the recently introduced KITTI360 dataset. Our experiments show that we can localize 65% of textual queries within 15m distance to query locations for top-10 retrieved locations. This is a starting point that we hope will spark future developments towards language-based navigation.

Cristiano Saltori, Aljoša Ošep, Elisa Ricci et al.

The ability to deploy robots that can operate safely in diverse environments is crucial for developing embodied intelligent agents. As a community, we have made tremendous progress in within-domain LiDAR semantic segmentation. However, do these methods generalize across domains? To answer this question, we design the first experimental setup for studying domain generalization (DG) for LiDAR semantic segmentation (DG-LSS). Our results confirm a significant gap between methods, evaluated in a cross-domain setting: for example, a model trained on the source dataset (SemanticKITTI) obtains $26.53$ mIoU on the target data, compared to $48.49$ mIoU obtained by the model trained on the target domain (nuScenes). To tackle this gap, we propose the first method specifically designed for DG-LSS, which obtains $34.88$ mIoU on the target domain, outperforming all baselines. Our method augments a sparse-convolutional encoder-decoder 3D segmentation network with an additional, dense 2D convolutional decoder that learns to classify a birds-eye view of the point cloud. This simple auxiliary task encourages the 3D network to learn features that are robust to sensor placement shifts and resolution, and are transferable across domains. With this work, we aim to inspire the community to develop and evaluate future models in such cross-domain conditions.

Adrià Caelles, Tim Meinhardt, Guillem Brasó et al.

Video Instance Segmentation (VIS) jointly tackles multi-object detection, tracking, and segmentation in video sequences. In the past, VIS methods mirrored the fragmentation of these subtasks in their architectural design, hence missing out on a joint solution. Transformers recently allowed to cast the entire VIS task as a single set-prediction problem. Nevertheless, the quadratic complexity of existing Transformer-based methods requires long training times, high memory requirements, and processing of low-single-scale feature maps. Deformable attention provides a more efficient alternative but its application to the temporal domain or the segmentation task have not yet been explored. In this work, we present Deformable VIS (DeVIS), a VIS method which capitalizes on the efficiency and performance of deformable Transformers. To reason about all VIS subtasks jointly over multiple frames, we present temporal multi-scale deformable attention with instance-aware object queries. We further introduce a new image and video instance mask head with multi-scale features, and perform near-online video processing with multi-cue clip tracking. DeVIS reduces memory as well as training time requirements, and achieves state-of-the-art results on the YouTube-VIS 2021, as well as the challenging OVIS dataset. Code is available at https://github.com/acaelles97/DeVIS.

Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner et al.

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that "similar objects should belong to the same group", the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We design a set of inference strategies tailored towards our algorithm, named Group Loss++ that further improve the results of our model. We show state-of-the-art results on clustering and image retrieval on four retrieval datasets, and present competitive results on two person re-identification datasets, providing a unified framework for retrieval and re-identification.

Aleksandr Kim, Guillem Brasó, Aljoša Ošep et al.

Most (3D) multi-object tracking methods rely on appearance-based cues for data association. By contrast, we investigate how far we can get by only encoding geometric relationships between objects in 3D space as cues for data-driven data association. We encode 3D detections as nodes in a graph, where spatial and temporal pairwise relations among objects are encoded via localized polar coordinates on graph edges. This representation makes our geometric relations invariant to global transformations and smooth trajectory changes, especially under non-holonomic motion. This allows our graph neural network to learn to effectively encode temporal and spatial interactions and fully leverage contextual and motion cues to obtain final scene interpretation by posing data association as edge classification. We establish a new state-of-the-art on nuScenes dataset and, more importantly, show that our method, PolarMOT, generalizes remarkably well across different locations (Boston, Singapore, Karlsruhe) and datasets (nuScenes and KITTI).

Tim Meinhardt, Matt Feiszli, Yuchen Fan et al.

Until recently, the Video Instance Segmentation (VIS) community operated under the common belief that offline methods are generally superior to a frame by frame online processing. However, the recent success of online methods questions this belief, in particular, for challenging and long video sequences. We understand this work as a rebuttal of those recent observations and an appeal to the community to focus on dedicated near-online VIS approaches. To support our argument, we present a detailed analysis on different processing paradigms and the new end-to-end trainable NOVIS (Near-Online Video Instance Segmentation) method. Our transformer-based model directly predicts spatio-temporal mask volumes for clips of frames and performs instance tracking between clips via overlap embeddings. NOVIS represents the first near-online VIS approach which avoids any handcrafted tracking heuristics. We outperform all existing VIS methods by large margins and provide new state-of-the-art results on both YouTube-VIS (2019/2021) and the OVIS benchmarks.

Anirudh S Chakravarthy, Meghana Reddy Ganesina, Peiyun Hu et al.

Addressing Lidar Panoptic Segmentation (LPS ) is crucial for safe deployment of autonomous vehicles. LPS aims to recognize and segment lidar points w.r.t. a pre-defined vocabulary of semantic classes, including thing classes of countable objects (e.g., pedestrians and vehicles) and stuff classes of amorphous regions (e.g., vegetation and road). Importantly, LPS requires segmenting individual thing instances (e.g., every single vehicle). Current LPS methods make an unrealistic assumption that the semantic class vocabulary is fixed in the real open world, but in fact, class ontologies usually evolve over time as robots encounter instances of novel classes that are considered to be unknowns w.r.t. the pre-defined class vocabulary. To address this unrealistic assumption, we study LPS in the Open World (LiPSOW): we train models on a dataset with a pre-defined semantic class vocabulary and study their generalization to a larger dataset where novel instances of thing and stuff classes can appear. This experimental setting leads to interesting conclusions. While prior art train class-specific instance segmentation methods and obtain state-of-the-art results on known classes, methods based on class-agnostic bottom-up grouping perform favorably on classes outside of the initial class vocabulary (i.e., unknown classes). Unfortunately, these methods do not perform on-par with fully data-driven methods on known classes. Our work suggests a middle ground: we perform class-agnostic point clustering and over-segment the input cloud in a hierarchical fashion, followed by binary point segment classification, akin to Region Proposal Network [1]. We obtain the final point cloud segmentation by computing a cut in the weighted hierarchical tree of point segments, independently of semantic classification. Remarkably, this unified approach leads to strong performance on both known and unknown classes.

Bingxin Ke, Qunjie Zhou, Jiahui Huang et al. · nvidia, utoronto

We introduce CAPA, a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion, using sparse geometric cues. Unlike prior methods that train task-specific encoders for auxiliary inputs, which often overfit and generalize poorly, CAPA freezes the FM backbone. Instead, it updates only a minimal set of parameters using Parameter-Efficient Fine-Tuning (e.g. LoRA or VPT), guided by gradients calculated directly from the sparse observations available at inference time. This approach effectively grounds the foundation model's geometric prior in the scene-specific measurements, correcting distortions and misplaced structures. For videos, CAPA introduces sequence-level parameter sharing, jointly adapting all frames to exploit temporal correlations, improve robustness, and enforce multi-frame consistency. CAPA is model-agnostic, compatible with any ViT-based FM, and achieves state-of-the-art results across diverse condition patterns on both indoor and outdoor datasets. Project page: research.nvidia.com/labs/dvl/projects/capa.

Jenny Seidenschwarz, Qunjie Zhou, Bardienus Duisterhof et al.

Reconstructing scenes and tracking motion are two sides of the same coin. Tracking points allow for geometric reconstruction [14], while geometric reconstruction of (dynamic) scenes allows for 3D tracking of points over time [24, 39]. The latter was recently also exploited for 2D point tracking to overcome occlusion ambiguities by lifting tracking directly into 3D [38]. However, above approaches either require offline processing or multi-view camera setups both unrealistic for real-world applications like robot navigation or mixed reality. We target the challenge of online 2D and 3D point tracking from unposed monocular camera input introducing Dynamic Online Monocular Reconstruction (DynOMo). We leverage 3D Gaussian splatting to reconstruct dynamic scenes in an online fashion. Our approach extends 3D Gaussians to capture new content and object motions while estimating camera movements from a single RGB frame. DynOMo stands out by enabling emergence of point trajectories through robust image feature reconstruction and a novel similarity-enhanced regularization term, without requiring any correspondence-level supervision. It sets the first baseline for online point tracking with monocular unposed cameras, achieving performance on par with existing methods. We aim to inspire the community to advance online point tracking and reconstruction, expanding the applicability to diverse real-world scenarios.

Orcun Cetintas, Guillem Brasó, Laura Leal-Taixé

Tracking objects over long videos effectively means solving a spectrum of problems, from short-term association for un-occluded objects to long-term association for objects that are occluded and then reappear in the scene. Methods tackling these two tasks are often disjoint and crafted for specific scenarios, and top-performing approaches are often a mix of techniques, which yields engineering-heavy solutions that lack generality. In this work, we question the need for hybrid approaches and introduce SUSHI, a unified and scalable multi-object tracker. Our approach processes long clips by splitting them into a hierarchy of subclips, which enables high scalability. We leverage graph neural networks to process all levels of the hierarchy, which makes our model unified across temporal scales and highly general. As a result, we obtain significant improvements over state-of-the-art on four diverse datasets. Our code and models are available at bit.ly/sushi-mot.

Maxim Maximov, Tim Meinhardt, Ismail Elezi et al.

The advent of data-driven technology solutions is accompanied by an increasing concern with data privacy. This is of particular importance for human-centered image recognition tasks, such as pedestrian detection, re-identification, and tracking. To highlight the importance of privacy issues and motivate future research, we motivate and introduce the Pedestrian Dataset De-Identification (PDI) task. PDI evaluates the degree of de-identification and downstream task training performance for a given de-identification method. As a first baseline, we propose IncogniMOT, a two-stage full-body de-identification pipeline based on image synthesis via generative adversarial networks. The first stage replaces target pedestrians with synthetic identities. To improve downstream task performance, we then apply stage two, which blends and adapts the synthetic image parts into the data. To demonstrate the effectiveness of IncogniMOT, we generate a fully de-identified version of the MOT17 pedestrian tracking dataset and analyze its application as training data for pedestrian re-identification, detection, and tracking models. Furthermore, we show how our data is able to narrow the synthetic-to-real performance gap in a privacy-conscious manner.

Yi Wang, Zhitong Xiong, Chenying Liu et al.

Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downstream applications crucial to our planet. However, most existing efforts remain limited to fixed spectral sensors, focus solely on the Earth's surface, and overlook valuable metadata beyond imagery. In this work, we take a step towards next-generation EO foundation models with three key components: 1) Copernicus-Pretrain, a massive-scale pretraining dataset that integrates 18.7M aligned images from all major Copernicus Sentinel missions, spanning from the Earth's surface to its atmosphere; 2) Copernicus-FM, a unified foundation model capable of processing any spectral or non-spectral sensor modality using extended dynamic hypernetworks and flexible metadata encoding; and 3) Copernicus-Bench, a systematic evaluation benchmark with 15 hierarchical downstream tasks ranging from preprocessing to specialized applications for each Sentinel mission. Our dataset, model, and benchmark greatly improve the scalability, versatility, and multimodal adaptability of EO foundation models, while also creating new opportunities to connect EO, weather, and climate research. Codes, datasets and models are available at https://github.com/zhu-xlab/Copernicus-FM.

Xuanchi Ren, Yifan Lu, Tianshi Cao et al. · nvidia, utoronto

Collecting and annotating real-world data for safety-critical physical AI systems, such as Autonomous Vehicle (AV), is time-consuming and costly. It is especially challenging to capture rare edge cases, which play a critical role in training and testing of an AV system. To address this challenge, we introduce the Cosmos-Drive-Dreams - a synthetic data generation (SDG) pipeline that aims to generate challenging scenarios to facilitate downstream tasks such as perception and driving policy training. Powering this pipeline is Cosmos-Drive, a suite of models specialized from NVIDIA Cosmos world foundation model for the driving domain and are capable of controllable, high-fidelity, multi-view, and spatiotemporally consistent driving video generation. We showcase the utility of these models by applying Cosmos-Drive-Dreams to scale the quantity and diversity of driving datasets with high-fidelity and challenging scenarios. Experimentally, we demonstrate that our generated data helps in mitigating long-tail distribution problems and enhances generalization in downstream tasks such as 3D lane detection, 3D object detection and driving policy learning. We open source our pipeline toolkit, dataset and model weights through the NVIDIA's Cosmos platform. Project page: https://research.nvidia.com/labs/toronto-ai/cosmos_drive_dreams

Aljoša Ošep, Tim Meinhardt, Francesco Ferroni et al.

We propose the SAL (Segment Anything in Lidar) method consisting of a text-promptable zero-shot model for segmenting and classifying any object in Lidar, and a pseudo-labeling engine that facilitates model training without manual supervision. While the established paradigm for Lidar Panoptic Segmentation (LPS) relies on manual supervision for a handful of object classes defined a priori, we utilize 2D vision foundation models to generate 3D supervision ``for free''. Our pseudo-labels consist of instance masks and corresponding CLIP tokens, which we lift to Lidar using calibrated multi-modal data. By training our model on these labels, we distill the 2D foundation models into our Lidar SAL model. Even without manual labels, our model achieves $91\%$ in terms of class-agnostic segmentation and $54\%$ in terms of zero-shot Lidar Panoptic Segmentation of the fully supervised state-of-the-art. Furthermore, we outperform several baselines that do not distill but only lift image features to 3D. More importantly, we demonstrate that SAL supports arbitrary class prompts, can be easily extended to new datasets, and shows significant potential to improve with increasing amounts of self-labeled data. Code and models are available at this $\href{https://github.com/nv-dvl/segment-anything-lidar}{URL}$.

Neehar Peri, Jonathon Luiten, Mengtian Li et al.

Object detection and forecasting are fundamental components of embodied perception. These two problems, however, are largely studied in isolation by the community. In this paper, we propose an end-to-end approach for detection and motion forecasting based on raw sensor measurement as opposed to ground truth tracks. Instead of predicting the current frame locations and forecasting forward in time, we directly predict future object locations and backcast to determine where each trajectory began. Our approach not only improves overall accuracy compared to other modular or end-to-end baselines, it also prompts us to rethink the role of explicit tracking for embodied perception. Additionally, by linking future and current locations in a many-to-one manner, our approach is able to reason about multiple futures, a capability that was previously considered difficult for end-to-end approaches. We conduct extensive experiments on the popular nuScenes dataset and demonstrate the empirical effectiveness of our approach. In addition, we investigate the appropriateness of reusing standard forecasting metrics for an end-to-end setup, and find a number of limitations which allow us to build simple baselines to game these metrics. We address this issue with a novel set of joint forecasting and detection metrics that extend the commonly used AP metrics from the detection community to measuring forecasting accuracy. Our code is available at https://github.com/neeharperi/FutureDet

Guillem Brasó, Nikita Kister, Laura Leal-Taixé

We introduce CenterGroup, an attention-based framework to estimate human poses from a set of identity-agnostic keypoints and person center predictions in an image. Our approach uses a transformer to obtain context-aware embeddings for all detected keypoints and centers and then applies multi-head attention to directly group joints into their corresponding person centers. While most bottom-up methods rely on non-learnable clustering at inference, CenterGroup uses a fully differentiable attention mechanism that we train end-to-end together with our keypoint detector. As a result, our method obtains state-of-the-art performance with up to 2.5x faster inference time than competing bottom-up methods. Our code is available at https://github.com/dvl-tum/center-group .

Mark Weber, Huiyu Wang, Siyuan Qiao et al.

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed DeepLab model variants with pretrained checkpoints as well as model training and evaluation code, allowing the community to reproduce and further improve upon the state-of-art systems. To showcase the effectiveness of DeepLab2, our Panoptic-DeepLab employing Axial-SWideRNet as network backbone achieves 68.0% PQ or 83.5% mIoU on Cityscaspes validation set, with only single-scale inference and ImageNet-1K pretrained checkpoints. We hope that publicly sharing our library could facilitate future research on dense pixel labeling tasks and envision new applications of this technology. Code is made publicly available at \url{https://github.com/google-research/deeplab2}.

Matthijs Douze, Giorgos Tolias, Ed Pizzi et al.

This paper introduces a new benchmark for large-scale image similarity detection. This benchmark is used for the Image Similarity Challenge at NeurIPS'21 (ISC2021). The goal is to determine whether a query image is a modified copy of any image in a reference corpus of size 1~million. The benchmark features a variety of image transformations such as automated transformations, hand-crafted image edits and machine-learning based manipulations. This mimics real-life cases appearing in social media, for example for integrity-related problems dealing with misinformation and objectionable content. The strength of the image manipulations, and therefore the difficulty of the benchmark, is calibrated according to the performance of a set of baseline approaches. Both the query and reference set contain a majority of "distractor" images that do not match, which corresponds to a real-life needle-in-haystack setting, and the evaluation metric reflects that. We expect the DISC21 benchmark to promote image copy detection as an important and challenging computer vision task and refresh the state of the art. Code and data are available at https://github.com/facebookresearch/isc2021

Aleksandr Kim, Aljoša Ošep, Laura Leal-Taixé

Multi-object tracking (MOT) enables mobile robots to perform well-informed motion planning and navigation by localizing surrounding objects in 3D space and time. Existing methods rely on depth sensors (e.g., LiDAR) to detect and track targets in 3D space, but only up to a limited sensing range due to the sparsity of the signal. On the other hand, cameras provide a dense and rich visual signal that helps to localize even distant objects, but only in the image domain. In this paper, we propose EagerMOT, a simple tracking formulation that eagerly integrates all available object observations from both sensor modalities to obtain a well-informed interpretation of the scene dynamics. Using images, we can identify distant incoming objects, while depth estimates allow for precise trajectory localization as soon as objects are within the depth-sensing range. With EagerMOT, we achieve state-of-the-art results across several MOT tasks on the KITTI and NuScenes datasets. Our code is available at https://github.com/aleksandrkim61/EagerMOT.

Jenny Seidenschwarz, Ismail Elezi, Laura Leal-Taixé

The goal of metric learning is to learn a function that maps samples to a lower-dimensional space where similar samples lie closer than dissimilar ones. Particularly, deep metric learning utilizes neural networks to learn such a mapping. Most approaches rely on losses that only take the relations between pairs or triplets of samples into account, which either belong to the same class or two different classes. However, these methods do not explore the embedding space in its entirety. To this end, we propose an approach based on message passing networks that takes all the relations in a mini-batch into account. We refine embedding vectors by exchanging messages among all samples in a given batch allowing the training process to be aware of its overall structure. Since not all samples are equally important to predict a decision boundary, we use an attention mechanism during message passing to allow samples to weigh the importance of each neighbor accordingly. We achieve state-of-the-art results on clustering and image retrieval on the CUB-200-2011, Cars196, Stanford Online Products, and In-Shop Clothes datasets. To facilitate further research, we make available the code and the models at https://github.com/dvl-tum/intra_batch_connections.

Tim Meinhardt, Alexander Kirillov, Laura Leal-Taixe et al.

The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task as a frame-to-frame set prediction problem and introduce TrackFormer, an end-to-end trainable MOT approach based on an encoder-decoder Transformer architecture. Our model achieves data association between frames via attention by evolving a set of track predictions through a video sequence. The Transformer decoder initializes new tracks from static object queries and autoregressively follows existing tracks in space and time with the conceptually new and identity preserving track queries. Both query types benefit from self- and encoder-decoder attention on global frame-level features, thereby omitting any additional graph optimization or modeling of motion and/or appearance. TrackFormer introduces a new tracking-by-attention paradigm and while simple in its design is able to achieve state-of-the-art performance on the task of multi-object tracking (MOT17 and MOT20) and segmentation (MOTS20). The code is available at https://github.com/timmeinhardt/trackformer .

Qunjie Zhou, Torsten Sattler, Laura Leal-Taixe

The classical matching pipeline used for visual localization typically involves three steps: (i) local feature detection and description, (ii) feature matching, and (iii) outlier rejection. Recently emerged correspondence networks propose to perform those steps inside a single network but suffer from low matching resolution due to the memory bottleneck. In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them. We present Patch2Pix, a novel refinement network that refines match proposals by regressing pixel-level matches from the local regions defined by those proposals and jointly rejecting outlier matches with confidence scores. Patch2Pix is weakly supervised to learn correspondences that are consistent with the epipolar geometry of an input image pair. We show that our refinement network significantly improves the performance of correspondence networks on image matching, homography estimation, and localization tasks. In addition, we show that our learned refinement generalizes to fully-supervised methods without re-training, which leads us to state-of-the-art localization performance. The code is available at https://github.com/GrumpyZhou/patch2pix.

Tim Meinhardt, Laura Leal-Taixe

Video object segmentation (VOS) describes the task of segmenting a set of objects in each frame of a video. In the semi-supervised setting, the first mask of each object is provided at test time. Following the one-shot principle, fine-tuning VOS methods train a segmentation model separately on each given object mask. However, recently the VOS community has deemed such a test time optimization and its impact on the test runtime as unfeasible. To mitigate the inefficiencies of previous fine-tuning approaches, we present efficient One-Shot Video Object Segmentation (e-OSVOS). In contrast to most VOS approaches, e-OSVOS decouples the object detection task and predicts only local segmentation masks by applying a modified version of Mask R-CNN. The one-shot test runtime and performance are optimized without a laborious and handcrafted hyperparameter search. To this end, we meta learn the model initialization and learning rates for the test time optimization. To achieve optimal learning behavior, we predict individual learning rates at a neuron level. Furthermore, we apply an online adaptation to address the common performance degradation throughout a sequence by continuously fine-tuning the model on previous mask predictions supported by a frame-to-frame bounding box propagation. e-OSVOS provides state-of-the-art results on DAVIS 2016, DAVIS 2017, and YouTube-VOS for one-shot fine-tuning methods while reducing the test runtime substantially. Code is available at https://github.com/dvl-tum/e-osvos.

Sabarinath Mahadevan, Ali Athar, Aljoša Ošep et al.

The task of object segmentation in videos is usually accomplished by processing appearance and motion information separately using standard 2D convolutional networks, followed by a learned fusion of the two sources of information. On the other hand, 3D convolutional networks have been successfully applied for video classification tasks, but have not been leveraged as effectively to problems involving dense per-pixel interpretation of videos compared to their 2D convolutional counterparts and lag behind the aforementioned networks in terms of performance. In this work, we show that 3D CNNs can be effectively applied to dense video prediction tasks such as salient object segmentation. We propose a simple yet effective encoder-decoder network architecture consisting entirely of 3D convolutions that can be trained end-to-end using a standard cross-entropy loss. To this end, we leverage an efficient 3D encoder, and propose a 3D decoder architecture, that comprises novel 3D Global Convolution layers and 3D Refinement modules. Our approach outperforms existing state-of-the-arts by a large margin on the DAVIS'16 Unsupervised, FBMS and ViSal dataset benchmarks in addition to being faster, thus showing that our architecture can efficiently learn expressive spatio-temporal features and produce high quality video segmentation masks. We have made our code and trained models publicly available at https://github.com/sabarim/3DC-Seg.

Ali Athar, Sabarinath Mahadevan, Aljoša Ošep et al.

Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in individual frames, and then associate these detections over time. Hence, these methods are often non-end-to-end trainable and highly tailored to specific tasks. In this paper, we propose a different approach that is well-suited to a variety of tasks involving instance segmentation in videos. In particular, we model a video clip as a single 3D spatio-temporal volume, and propose a novel approach that segments and tracks instances across space and time in a single stage. Our problem formulation is centered around the idea of spatio-temporal embeddings which are trained to cluster pixels belonging to a specific object instance over an entire video clip. To this end, we introduce (i) novel mixing functions that enhance the feature representation of spatio-temporal embeddings, and (ii) a single-stage, proposal-free network that can reason about temporal context. Our network is trained end-to-end to learn spatio-temporal embeddings as well as parameters required to cluster these embeddings, thus simplifying inference. Our method achieves state-of-the-art results across multiple datasets and tasks. Code and models are available at https://github.com/sabarim/STEm-Seg.

Guillem Brasó, Laura Leal-Taixé

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such \textit{structured domain} is not trivial. As a consequence, most learning-based work has been devoted to learning better features for MOT, and then using these with well-established optimization frameworks. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and predict final solutions. Hence, we show that learning in MOT does not need to be restricted to feature extraction, but it can also be applied to the data association step. We show a significant improvement in both MOTA and IDF1 on three publicly available benchmarks. Our code is available at https://bit.ly/motsolv .

Yihong Xu, Aljosa Osep, Yutong Ban et al.

The recent trend in vision-based multi-object tracking (MOT) is heading towards leveraging the representational power of deep learning to jointly learn to detect and track objects. However, existing methods train only certain sub-modules using loss functions that often do not correlate with established tracking evaluation measures such as Multi-Object Tracking Accuracy (MOTA) and Precision (MOTP). As these measures are not differentiable, the choice of appropriate loss functions for end-to-end training of multi-object tracking methods is still an open research problem. In this paper, we bridge this gap by proposing a differentiable proxy of MOTA and MOTP, which we combine in a loss function suitable for end-to-end training of deep multi-object trackers. As a key ingredient, we propose a Deep Hungarian Net (DHN) module that approximates the Hungarian matching algorithm. DHN allows estimating the correspondence between object tracks and ground truth objects to compute differentiable proxies of MOTA and MOTP, which are in turn used to optimize deep trackers directly. We experimentally demonstrate that the proposed differentiable framework improves the performance of existing multi-object trackers, and we establish a new state of the art on the MOTChallenge benchmark. Our code is publicly available from https://github.com/yihongXU/deepMOT.

Aysim Toker, Marvin Eisenberger, Daniel Cremers et al.

In recent years, semantic segmentation has become a pivotal tool in processing and interpreting satellite imagery. Yet, a prevalent limitation of supervised learning techniques remains the need for extensive manual annotations by experts. In this work, we explore the potential of generative image diffusion to address the scarcity of annotated data in earth observation tasks. The main idea is to learn the joint data manifold of images and labels, leveraging recent advancements in denoising diffusion probabilistic models. To the best of our knowledge, we are the first to generate both images and corresponding masks for satellite segmentation. We find that the obtained pairs not only display high quality in fine-scale features but also ensure a wide sampling diversity. Both aspects are crucial for earth observation data, where semantic classes can vary severely in scale and occurrence frequency. We employ the novel data instances for downstream segmentation, as a form of data augmentation. In our experiments, we provide comparisons to prior works based on discriminative diffusion models or GANs. We demonstrate that integrating generated samples yields significant quantitative improvements for satellite semantic segmentation -- both compared to baselines and when training only on the original data.

Sven Elflein, Qunjie Zhou, Sérgio Agostinho et al.

We present Light3R-SfM, a feed-forward, end-to-end learnable framework for efficient large-scale Structure-from-Motion (SfM) from unconstrained image collections. Unlike existing SfM solutions that rely on costly matching and global optimization to achieve accurate 3D reconstructions, Light3R-SfM addresses this limitation through a novel latent global alignment module. This module replaces traditional global optimization with a learnable attention mechanism, effectively capturing multi-view constraints across images for robust and precise camera pose estimation. Light3R-SfM constructs a sparse scene graph via retrieval-score-guided shortest path tree to dramatically reduce memory usage and computational overhead compared to the naive approach. Extensive experiments demonstrate that Light3R-SfM achieves competitive accuracy while significantly reducing runtime, making it ideal for 3D reconstruction tasks in real-world applications with a runtime constraint. This work pioneers a data-driven, feed-forward SfM approach, paving the way toward scalable, accurate, and efficient 3D reconstruction in the wild.

Jenny Seidenschwarz, Aljoša Ošep, Francesco Ferroni et al.

We tackle semi-supervised object detection based on motion cues. Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects and use these as supervisory signals to train 3D object detectors in Lidar data without manual supervision. We re-think this approach and suggest that both, object detection, as well as motion-inspired pseudo-labeling, can be tackled in a data-driven manner. We leverage recent advances in scene flow estimation to obtain point trajectories from which we extract long-term, class-agnostic motion patterns. Revisiting correlation clustering in the context of message passing networks, we learn to group those motion patterns to cluster points to object instances. By estimating the full extent of the objects, we obtain per-scan 3D bounding boxes that we use to supervise a Lidar object detection network. Our method not only outperforms prior heuristic-based approaches (57.5 AP, +14 improvement over prior work), more importantly, we show we can pseudo-label and train object detectors across datasets.

Yuan-Hong Liao, Sven Elflein, Liu He et al. · utoronto

Recent reasoning models through test-time scaling have demonstrated that long chain-of-thoughts can unlock substantial performance boosts in hard reasoning tasks such as math and code. However, the benefit of such long thoughts for system-2 reasoning is relatively less explored in other domains such as perceptual tasks where shallower, system-1 reasoning seems sufficient. In this paper, we introduce LongPerceptualThoughts, a new synthetic dataset with 30K long-thought traces for perceptual tasks. The key challenges in synthesizing elaborate reasoning thoughts for perceptual tasks are that off-the-shelf models are not yet equipped with such thinking behavior and that it is not straightforward to build a reliable process verifier for perceptual tasks. Thus, we propose a novel three-stage data synthesis framework that first synthesizes verifiable multiple-choice questions from dense image descriptions, then extracts simple CoTs from VLMs for those verifiable problems, and finally expands those simple thoughts to elaborate long thoughts via frontier reasoning models. In controlled experiments with a strong instruction-tuned 7B model, we demonstrate notable improvements over existing visual reasoning data-generation methods. Our model, trained on the generated dataset, achieves an average +3.4 points improvement over 5 vision-centric benchmarks, including +11.8 points on V$^*$ Bench. Notably, despite being tuned for vision tasks, it also improves performance on the text reasoning benchmark, MMLU-Pro, by +2 points.

Ayca Takmaz, Cristiano Saltori, Neehar Peri et al.

We propose CAL (Complete Anything in Lidar) for Lidar-based shape-completion in-the-wild. This is closely related to Lidar-based semantic/panoptic scene completion. However, contemporary methods can only complete and recognize objects from a closed vocabulary labeled in existing Lidar datasets. Different to that, our zero-shot approach leverages the temporal context from multi-modal sensor sequences to mine object shapes and semantic features of observed objects. These are then distilled into a Lidar-only instance-level completion and recognition model. Although we only mine partial shape completions, we find that our distilled model learns to infer full object shapes from multiple such partial observations across the dataset. We show that our model can be prompted on standard benchmarks for Semantic and Panoptic Scene Completion, localize objects as (amodal) 3D bounding boxes, and recognize objects beyond fixed class vocabularies. Our project page is https://research.nvidia.com/labs/dvl/projects/complete-anything-lidar

Yushan Zhang, Aljoša Ošep, Laura Leal-Taixé et al.

Zero-shot 4D segmentation and recognition of arbitrary objects in Lidar is crucial for embodied navigation, with applications ranging from streaming perception to semantic mapping and localization. However, the primary challenge in advancing research and developing generalized, versatile methods for spatio-temporal scene understanding in Lidar lies in the scarcity of datasets that provide the necessary diversity and scale of annotations.To overcome these challenges, we propose SAL-4D (Segment Anything in Lidar--4D), a method that utilizes multi-modal robotic sensor setups as a bridge to distill recent developments in Video Object Segmentation (VOS) in conjunction with off-the-shelf Vision-Language foundation models to Lidar. We utilize VOS models to pseudo-label tracklets in short video sequences, annotate these tracklets with sequence-level CLIP tokens, and lift them to the 4D Lidar space using calibrated multi-modal sensory setups to distill them to our SAL-4D model. Due to temporal consistent predictions, we outperform prior art in 3D Zero-Shot Lidar Panoptic Segmentation (LPS) over $5$ PQ, and unlock Zero-Shot 4D-LPS.

Fei Xue, Sven Elflein, Laura Leal-Taixé et al.

Establishing correspondences across images is a fundamental challenge in computer vision, underpinning tasks like Structure-from-Motion, image editing, and point tracking. Traditional methods are often specialized for specific correspondence types, geometric, semantic, or temporal, whereas humans naturally identify alignments across these domains. Inspired by this flexibility, we propose MATCHA, a unified feature model designed to ``rule them all'', establishing robust correspondences across diverse matching tasks. Building on insights that diffusion model features can encode multiple correspondence types, MATCHA augments this capacity by dynamically fusing high-level semantic and low-level geometric features through an attention-based module, creating expressive, versatile, and robust features. Additionally, MATCHA integrates object-level features from DINOv2 to further boost generalization, enabling a single feature capable of matching anything. Extensive experiments validate that MATCHA consistently surpasses state-of-the-art methods across geometric, semantic, and temporal matching tasks, setting a new foundation for a unified approach for the fundamental correspondence problem in computer vision. To the best of our knowledge, MATCHA is the first approach that is able to effectively tackle diverse matching tasks with a single unified feature.

Orcun Cetintas, Tim Meinhardt, Guillem Brasó et al.

Increasing the annotation efficiency of trajectory annotations from videos has the potential to enable the next generation of data-hungry tracking algorithms to thrive on large-scale datasets. Despite the importance of this task, there are currently very few works exploring how to efficiently label tracking datasets comprehensively. In this work, we introduce SPAM, a video label engine that provides high-quality labels with minimal human intervention. SPAM is built around two key insights: i) most tracking scenarios can be easily resolved. To take advantage of this, we utilize a pre-trained model to generate high-quality pseudo-labels, reserving human involvement for a smaller subset of more difficult instances; ii) handling the spatiotemporal dependencies of track annotations across time can be elegantly and efficiently formulated through graphs. Therefore, we use a unified graph formulation to address the annotation of both detections and identity association for tracks across time. Based on these insights, SPAM produces high-quality annotations with a fraction of ground truth labeling cost. We demonstrate that trackers trained on SPAM labels achieve comparable performance to those trained on human annotations while requiring only $3-20\%$ of the human labeling effort. Hence, SPAM paves the way towards highly efficient labeling of large-scale tracking datasets. We release all models and code.