We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3D understanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation. Accurately reconstructing such interactions in 3D is challenging due to heavy occlusion, viewpoint bias, camera distortion, and motion blur from the head movement. To this end, we designed the HANDS23 challenge based on the AssemblyHands and ARCTIC datasets with carefully designed training and testing splits. Based on the results of the top submitted methods and more recent baselines on the leaderboards, we perform a thorough analysis on 3D hand(-object) reconstruction tasks. Our analysis demonstrates the effectiveness of addressing distortion specific to egocentric cameras, adopting high-capacity transformers to learn complex hand-object interactions, and fusing predictions from different views. Our study further reveals challenging scenarios intractable with state-of-the-art methods, such as fast hand motion, object reconstruction from narrow egocentric views, and close contact between two hands and objects. Our efforts will enrich the community's knowledge foundation and facilitate future hand studies on egocentric hand-object interactions.
This study investigates the application of ordinal regression methods for categorizing disease severity in chest radiographs. We propose a framework that divides the ordinal regression problem into three parts: a model, a target function, and a classification function. Different encoding methods, including one-hot, Gaussian, progress-bar, and our soft-progress-bar, are applied using ResNet50 and ViT-B-16 deep learning models. We show that the choice of encoding has a strong impact on performance and that the best encoding depends on the chosen weighting of Cohen's kappa and also on the model architecture used. We make our code publicly available on GitHub.
Current state-of-the-art Video Object Segmentation (VOS) methods rely on dense per-object mask annotations both during training and testing. This requires time-consuming and costly video annotation mechanisms. We propose a novel Point-VOS task with a spatio-temporally sparse point-wise annotation scheme that substantially reduces the annotation effort. We apply our annotation scheme to two large-scale video datasets with text descriptions and annotate over 19M points across 133K objects in 32K videos. Based on our annotations, we propose a new Point-VOS benchmark, and a corresponding point-based training mechanism, which we use to establish strong baseline results. We show that existing VOS methods can easily be adapted to leverage our point annotations during training, and can achieve results close to the fully-supervised performance when trained on pseudo-masks generated from these points. In addition, we show that our data can be used to improve models that connect vision and language, by evaluating it on the Video Narrative Grounding (VNG) task. We will make our code and annotations available at https://pointvos.github.io.
Background: Cell segmentation in bright-field histological slides is a crucial topic in medical image analysis. Having access to accurate segmentation allows researchers to examine the relationship between cellular morphology and clinical observations. Unfortunately, most segmentation methods known today are limited to nuclei and cannot segmentate the cytoplasm. Material & Methods: We present a new network architecture Cyto R-CNN that is able to accurately segment whole cells (with both the nucleus and the cytoplasm) in bright-field images. We also present a new dataset CytoNuke, consisting of multiple thousand manual annotations of head and neck squamous cell carcinoma cells. Utilizing this dataset, we compared the performance of Cyto R-CNN to other popular cell segmentation algorithms, including QuPath's built-in algorithm, StarDist and Cellpose. To evaluate segmentation performance, we calculated AP50, AP75 and measured 17 morphological and staining-related features for all detected cells. We compared these measurements to the gold standard of manual segmentation using the Kolmogorov-Smirnov test. Results: Cyto R-CNN achieved an AP50 of 58.65% and an AP75 of 11.56% in whole-cell segmentation, outperforming all other methods (QuPath $19.46/0.91\%$; StarDist $45.33/2.32\%$; Cellpose $31.85/5.61\%$). Cell features derived from Cyto R-CNN showed the best agreement to the gold standard ($\bar{D} = 0.15$) outperforming QuPath ($\bar{D} = 0.22$), StarDist ($\bar{D} = 0.25$) and Cellpose ($\bar{D} = 0.23$). Conclusion: Our newly proposed Cyto R-CNN architecture outperforms current algorithms in whole-cell segmentation while providing more reliable cell measurements than any other model. This could improve digital pathology workflows, potentially leading to improved diagnosis. Moreover, our published dataset can be used to develop further models in the future.
Manually creating 3D environments for AR/VR applications is a complex process requiring expert knowledge in 3D modeling software. Pioneering works facilitate this process by generating room meshes conditioned on textual style descriptions. Yet, many of these automatically generated 3D meshes do not adhere to typical room layouts, compromising their plausibility, e.g., by placing several beds in one bedroom. To address these challenges, we present ControlRoom3D, a novel method to generate high-quality room meshes. Central to our approach is a user-defined 3D semantic proxy room that outlines a rough room layout based on semantic bounding boxes and a textual description of the overall room style. Our key insight is that when rendered to 2D, this 3D representation provides valuable geometric and semantic information to control powerful 2D models to generate 3D consistent textures and geometry that aligns well with the proxy room. Backed up by an extensive study including quantitative metrics and qualitative user evaluations, our method generates diverse and globally plausible 3D room meshes, thus empowering users to design 3D rooms effortlessly without specialized knowledge.
We report on our effort to create a corpus dataset of different social context situations in an office setting for further disciplinary and interdisciplinary research in computer vision, psychology, and human-robot-interaction. For social robots to be able to behave appropriately, they need to be aware of the social context they act in. Consider, for example, a robot with the task to deliver a personal message to a person. If the person is arguing with an office mate at the time of message delivery, it might be more appropriate to delay playing the message as to respect the recipient's privacy and not to interfere with the current situation. This can only be done if the situation is classified correctly and in a second step if an appropriate behavior is chosen that fits the social situation. Our work aims to enable robots accomplishing the task of classifying social situations by creating a dataset composed of semantically annotated video scenes of office situations from television soap operas. The dataset can then serve as a basis for conducting research in both computer vision and human-robot interaction.
Accurately perceiving and tracking instances over time is essential for the decision-making processes of autonomous agents interacting safely in dynamic environments. With this intention, we propose Mask4D for the challenging task of 4D panoptic segmentation of LiDAR point clouds. Mask4D is the first transformer-based approach unifying semantic instance segmentation and tracking of sparse and irregular sequences of 3D point clouds into a single joint model. Our model directly predicts semantic instances and their temporal associations without relying on any hand-crafted non-learned association strategies such as probabilistic clustering or voting-based center prediction. Instead, Mask4D introduces spatio-temporal instance queries which encode the semantic and geometric properties of each semantic tracklet in the sequence. In an in-depth study, we find that it is critical to promote spatially compact instance predictions as spatio-temporal instance queries tend to merge multiple semantically similar instances, even if they are spatially distant. To this end, we regress 6-DOF bounding box parameters from spatio-temporal instance queries, which is used as an auxiliary task to foster spatially compact predictions. Mask4D achieves a new state-of-the-art on the SemanticKITTI test set with a score of 68.4 LSTQ, improving upon published top-performing methods by at least +4.5%.
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work that models scenes as a collection of 3D Gaussians which are optimized to reconstruct input images via differentiable rendering. To model dynamic scenes, we allow Gaussians to move and rotate over time while enforcing that they have persistent color, opacity, and size. By regularizing Gaussians' motion and rotation with local-rigidity constraints, we show that our Dynamic 3D Gaussians correctly model the same area of physical space over time, including the rotation of that space. Dense 6-DOF tracking and dynamic reconstruction emerges naturally from persistent dynamic view synthesis, without requiring any correspondence or flow as input. We demonstrate a large number of downstream applications enabled by our representation, including first-person view synthesis, dynamic compositional scene synthesis, and 4D video editing.
A single unexpected object on the road can cause an accident or may lead to injuries. To prevent this, we need a reliable mechanism for finding anomalous objects on the road. This task, called anomaly segmentation, can be a stepping stone to safe and reliable autonomous driving. Current approaches tackle anomaly segmentation by assigning an anomaly score to each pixel and by grouping anomalous regions using simple heuristics. However, pixel grouping is a limiting factor when it comes to evaluating the segmentation performance of individual anomalous objects. To address the issue of grouping multiple anomaly instances into one, we propose an approach that produces accurate anomaly instance masks. Our approach centers on an out-of-distribution segmentation model for identifying uncertain regions and a strong generalist segmentation model for anomaly instances segmentation. We investigate ways to use uncertain regions to guide such a segmentation model to perform segmentation of anomalous instances. By incorporating strong object priors from a generalist model we additionally improve the per-pixel anomaly segmentation performance. Our approach outperforms current pixel-level anomaly segmentation methods, achieving an AP of 80.08% and 88.98% on the Fishyscapes Lost and Found and the RoadAnomaly validation sets respectively. Project page: https://vision.rwth-aachen.de/ugains
During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point to an object (or the background), while the user corrects errors in the resulting segmentation and feeds them back into the model. From a machine learning perspective the goal is to design the model and the feedback mechanism in a way that minimizes the required user input. The current best practice segments objects one at a time, and asks the user to provide positive clicks to indicate regions wrongly assigned to the background and negative clicks to indicate regions wrongly assigned to the object (foreground). Sequentially visiting objects is wasteful, since it disregards synergies between objects: a positive click for a given object can, by definition, serve as a negative click for nearby objects, moreover a direct competition between adjacent objects can speed up the identification of their common boundary. We introduce AGILE3D, an efficient, attention-based model that (1) supports simultaneous segmentation of multiple 3D objects, (2) yields more accurate segmentation masks with fewer user clicks, and (3) offers faster inference. We encode the point cloud into a latent feature representation, and view user clicks as queries and employ cross-attention to represent contextual relations between different click locations as well as between clicks and the 3D point cloud features. Every time new clicks are added, we only need to run a lightweight decoder that produces updated segmentation masks. In experiments with four different point cloud datasets, AGILE3D sets a new state of the art, moreover, we also verify its practicality in real-world setups with a real user study.