Research Group Benjamin Busam

Typical template-based object pose pipelines estimate the pose by retrieving the closest matching template and aligning it with the observed image. However, failure to retrieve the correct template often leads to inaccurate pose predictions. To address this, we reformulate template-based object pose estimation as a ray alignment problem, where the viewing directions from multiple posed template images are learned to align with a non-posed query image. Inspired by recent progress in diffusion-based camera pose estimation, we embed this formulation into a diffusion transformer architecture that aligns a query image with a set of posed templates. We reparameterize object rotation using object-centered camera rays and model object translation by extending scale-invariant translation estimation to dense translation offsets. Our model leverages geometric priors from the templates to guide accurate query pose inference. A coarse-to-fine training strategy based on narrowed template sampling improves performance without modifying the network architecture. Extensive experiments across multiple benchmark datasets show competitive results of our method compared to state-of-the-art approaches in unseen object pose estimation.

Few-shot anomaly detection streamlines and simplifies industrial safety inspection. However, limited samples make accurate differentiation between normal and abnormal features challenging, and even more so under category-agnostic conditions. Large-scale pre-training of foundation visual encoders has advanced many fields, as the enormous quantity of data helps to learn the general distribution of normal images. We observe that the anomaly amount in an image directly correlates with the difference in the learnt embeddings and utilize this to design a few-shot anomaly detector termed FoundAD. This is done by learning a nonlinear projection operator onto the natural image manifold. The simple operator acts as an effective tool for anomaly detection to characterize and identify out-of-distribution regions in an image. Extensive experiments show that our approach supports multi-class detection and achieves competitive performance while using substantially fewer parameters than prior methods. Backed up by evaluations with multiple foundation encoders, including fresh DINOv3, we believe this idea broadens the perspective on foundation features and advances the field of few-shot anomaly detection.

Conversational AI tools for generating and discussing accurate radiology reports could transform radiology by enabling collaborative, human-in-the-loop diagnostic processes, saving time and enhancing report quality. While, to this end, Large Vision-Language Models hold promise, current methods lack clinical correctness or are single-task models without conversational abilities. We propose a novel architecture and dataset to address these limitations. First, we propose a secondary image branch, explicitly focusing on structured clinical findings, improving the clinical correctness score by 13.3%. Second, we propose a catastrophic forgetting mitigation strategy and instruct dataset with variable dialog-based tasks, to enable our model to handle a multitude of different queries. RaDialog marks a foundational step toward clinical dialog systems, outperforming existing medical LVLMs by 15.0% in clinical correctness in report generation, 23.4% in interactive report correction, and is preferred by radiologists in 84.0% of cases over a comparative method.

A key challenge in model-free category-level pose estimation is the extraction of contextual object features that generalize across varying instances within a specific category. Recent approaches leverage foundational features to capture semantic and geometry cues from data. However, these approaches fail under partial visibility. We overcome this with a first-complete-then-aggregate strategy for feature extraction utilizing class priors. In this paper, we present GCE-Pose, a method that enhances pose estimation for novel instances by integrating category-level global context prior. GCE-Pose performs semantic shape reconstruction with a proposed Semantic Shape Reconstruction (SSR) module. Given an unseen partial RGB-D object instance, our SSR module reconstructs the instance’s global geometry and semantics by deforming category-specific 3D semantic prototypes through a learned deep Linear Shape Model. We further introduce a Global Context Enhanced (GCE) feature fusion module that effectively fuses features from partial RGB-D observations and the reconstructed global context. Extensive experiments validate the impact of our global context prior and the effectiveness of the GCE fusion module, demonstrating that GCE-Pose significantly outperforms existing methods on challenging real-world datasets HouseCat6D and NOCS-REAL275.

Operating rooms (ORs) are complex, high-stakes environments requiring precise understanding of interactions among medical staff, tools, and equipment for enhancing surgical assistance, situational awareness, and patient safety. Current datasets fall short in scale, realism and do not capture the multimodal nature of OR scenes, limiting progress in OR modeling. To this end, we introduce MM-OR, a realistic and large-scale multimodal spatiotemporal OR dataset, and the first dataset to enable multimodal scene graph generation. MM-OR captures comprehensive OR scenes containing RGB-D data, detail views, audio, speech transcripts, robotic logs, and tracking data and is annotated with panoptic segmentations, semantic scene graphs, and downstream task labels. Further, we propose MM2SG, the first multimodal large vision-language model for scene graph generation, and through extensive experiments, demonstrate its ability to effectively leverage multimodal inputs. Together, MM-OR and MM2SG establish a new benchmark for holistic OR understanding, and open the path towards multimodal scene analysis in complex, high-stakes environments.

Scene Graph Generation (SGG) is a visual understanding task that describes a scene as a graph of entities and their relationships, traditionally relying on spatial labels like bounding boxes or segmentation masks. These requirements increase annotation costs and complicate integration with other modalities where spatial synchronization may be unavailable. In this work, we investigate the feasibility and effectiveness of scene graphs without location information, offering an alternative paradigm for scenarios where spatial data is unavailable. To this end, we propose the first method to generate location-free scene graphs, directly from images, evaluate their correctness and show the usefulness of such location-free scene graphs in several downstream tasks. Our proposed method, Pix2SG, models scene graph generation as an autoregressive sequence modeling task, predicting all instances and their relations as one output sequence. To enable evaluation without location matching, we propose a heuristic tree search algorithm that matches predicted scene graphs with ground truth graphs, bypassing the need for location-based metrics. We demonstrate the effectiveness of location-free scene graphs on three benchmark datasets and two downstream tasks – image retrieval and visual question showing they can achieve competitive performance with significantly less annotations. Our findings suggest that location-free scene graphs can still be generated and utilized effectively without location information, thus opening new avenues for scalable, structured and efficient visual representations, such as for multimodal scene understanding by reducing dependency on modality-specific annotations. The code will be made available upon acceptance.

We introduce XYZ-IBD, a bin-picking dataset for 6D pose estimation that captures real-world industrial complexity, including challenging object geometries, reflective materials, severe occlusions, and dense clutter. The dataset reflects authentic robotic manipulation scenarios with millimeter-accurate annotations. Unlike existing datasets that primarily focus on household objects, which approach saturation,XYZ-IBD represents the unsolved realistic industrial conditions. The dataset features 15 texture-less, metallic, and mostly symmetrical objects of varying shapes and sizes. These objects are heavily occluded and randomly arranged in bins with high density, replicating the challenges of real-world bin-picking. XYZ-IBD was collected using two high-precision industrial cameras and one commercially available camera, providing RGB, grayscale, and depth images. It contains 75 multi-view real-world scenes, along with a large-scale synthetic dataset rendered under simulated bin-picking conditions. We employ a meticulous annotation pipeline that includes anti-reflection spray, multi-view depth fusion, and semi-automatic annotation, achieving millimeter-level pose labeling accuracy required for industrial manipulation. Quantification in simulated environments confirms the reliability of the ground-truth annotations. We benchmark state-of-the-art methods on 2D detection, 6D pose estimation, and depth estimation tasks on our dataset, revealing significant performance degradation in our setups compared to current academic household benchmarks. By capturing the complexity of real-world bin-picking scenarios, XYZ-IBD introduces more realistic and challenging problems for future research.

Operating rooms (ORs) demand precise coordination among surgeons, nurses, and equipment in a fast-paced, occlusion-heavy environment, necessitating advanced perception models to enhance safety and efficiency. Existing datasets either provide partial egocentric views or sparse exocentric multi-view context, but do not explore the comprehensive combination of both. We introduce EgoExOR, the first OR dataset and accompanying benchmark to fuse first-person and third-person perspectives. Spanning 94 minutes (84,553 frames at 15 FPS) of two emulated spine procedures, Ultrasound-Guided Needle Insertion and Minimally Invasive Spine Surgery, EgoExOR integrates egocentric data (RGB, gaze, hand tracking, audio) from wearable glasses, exocentric RGB and depth from RGB-D cameras, and ultrasound imagery. Its detailed scene graph annotations, covering 36 entities and 22 relations (568,235 triplets), enable robust modeling of clinical interactions, supporting tasks like action recognition and human-centric perception. We evaluate the surgical scene graph generation performance of two adapted state-of-the-art models and offer a new baseline that explicitly leverages EgoExOR’s multimodal and multi-perspective signals. This new dataset and benchmark set a new foundation for OR perception, offering a rich, multimodal resource for next-generation clinical perception.

Data augmentation is widely used to train deep learning models to address data scarcity. However, traditional data augmentation (TDA) typically relies on simple geometric transformation, such as random rotation and rescaling, resulting in minimal data diversity enrichment and limited model performance improvement. State-of-the-art generative models for 3D shape generation rely on the denoising diffusion probabilistic models and manage to generate realistic novel point clouds for 3D content creation and manipulation. Nevertheless, the generated 3D shapes lack associated point-wise semantic labels, restricting their usage in enlarging the training data for point cloud segmentation tasks. To bridge the gap between data augmentation techniques and the advanced diffusion models, we extend the state-of-the-art 3D diffusion model, Lion, to a part-aware generative model that can generate high-quality point clouds conditioned on given segmentation masks. Leveraging the novel generative model, we introduce a 3-step generative data augmentation (GDA) pipeline for point cloud segmentation training. Our GDA approach requires only a small amount of labeled samples but enriches the training data with generated variants and pseudo-labeled samples, which are validated by a novel diffusion-based pseudo-label filtering method. Extensive experiments on two large-scale synthetic datasets and a real-world medical dataset demonstrate that our GDA method outperforms TDA approach and related semi-supervised and self-supervised methods.

Recent advances in the field of 6D pose estimation of unseen objects not present during training are promising, however, the performance gap between these general methods and object-specific methods remains significant. This paper introduces an innovative unsupervised test-time adaptation method, termed TTAPose, capable of adapting a pose estimator to any unseen object. TTAPose initially undergoes pre-training using a large synthetic dataset and thereafter refines the weights using unsupervised loss conducted on unseen real-world target objects. The network, based on a teacher-student architecture, leverages an RGB-D pose refinement pipeline to incrementally improve pseudo labels. Notably, TTAPose operates with no requirement for target data annotation, thus minimizing time and data expenditure. Experimental results show performance levels comparable to supervised methods, effectively narrowing the gap to object-specific baselines.

We present EchoScene, an interactive and controllable generative model that generates 3D indoor scenes on scene graphs. EchoScene leverages a dual-branch diffusion model that dynamically adapts to scene graphs. Existing methods struggle to handle scene graphs due to varying numbers of nodes, multiple edge combinations, and manipulator-induced node-edge operations. EchoScene overcomes this by associating each node with a denoising process and enables collaborative information exchange, enhancing controllable and consistent generation aware of global constraints. This is achieved through an information echo scheme in both shape and layout branches. At every denoising step, all processes share their denoising data with an information exchange unit that combines these updates using graph convolution. The scheme ensures that the denoising processes are influenced by a holistic understanding of the scene graph, facilitating the generation of globally coherent scenes. The resulting scenes can be manipulated during inference by editing the input scene graph and sampling the noise in the diffusion model. Extensive experiments validate our approach, which maintains scene controllability and surpasses previous methods in generation fidelity. Moreover, the generated scenes are of high quality and thus directly compatible with off-the-shelf texture generation. Code and trained models are open-sourced.

Object pose distribution estimation is crucial in robotics for better path planning and handling of symmetric objects. Recent distribution estimation approaches employ contrastive learning-based approaches by maximizing the likelihood of a single pose estimate in the absence of a CAD model. We propose a pose distribution estimation method leveraging symmetry respecting correspondence distributions and shape information obtained using a CAD model. Contrastive learning-based approaches require an exhaustive amount of training images from different viewpoints to learn the distribution properly, which is not possible in realistic scenarios. Instead, we propose a pipeline that can leverage correspondence distributions and shape information from the CAD model, which are later used to learn pose distributions. Besides, having access to pose distribution based on correspondences before learning pose distributions conditioned on images, can help formulate the loss between distributions. The prior knowledge of distribution also helps the network to focus on getting sharper modes instead. With the CAD prior, our approach converges much faster and learns distribution better by focusing on learning sharper distribution near all the valid modes, unlike contrastive approaches, which focus on a single mode at a time. We achieve benchmark results on SYMSOL-I and T-Less datasets.

We present EchoScene, an interactive and controllable generative model that generates 3D indoor scenes on scene graphs. EchoScene leverages a dual-branch diffusion model that dynamically adapts to scene graphs. Existing methods struggle to handle scene graphs due to varying numbers of nodes, multiple edge combinations, and manipulator-induced node-edge operations. EchoScene overcomes this by associating each node with a denoising process and enables collaborative information exchange, enhancing controllable and consistent generation aware of global constraints. This is achieved through an information echo scheme in both shape and layout branches. At every denoising step, all processes share their denoising data with an information exchange unit that combines these updates using graph convolution. The scheme ensures that the denoising processes are influenced by a holistic understanding of the scene graph, facilitating the generation of globally coherent scenes. The resulting scenes can be manipulated during inference by editing the input scene graph and sampling the noise in the diffusion model. Extensive experiments validate our approach, which maintains scene controllability and surpasses previous methods in generation fidelity. Moreover, the generated scenes are of high quality and thus directly compatible with off-the-shelf texture generation. Our code and models are open-sourced.

Reconstructing endoscopic scenes is vital for medical purposes, such as post-operative assessments and educational training. Recently, neural rendering has emerged as a promising method for reconstructing endoscopic scenes involving tissue deformation. Yet, current techniques exhibit major limitations, such as reliance on static endoscopes, limited deformation, or the need for external tracking devices to obtain camera pose data. In this paper we introduce a novel solution that can tackle these challenges posed by
a moving stereo endoscope in a highly deformable setting. Our method divides the scene into multiple overlapping 4D neural radiance fields (NeRFs) and uses a progressive optimization approach via optical flow and geometry supervision for simultaneous reconstruction and camera pose estimation. Tested on videos of up to fifteen times longer than what prior work experiment on, our method greatly improves usability, extending detailed reconstruction to much longer surgical videos without external tracking. Comprehensive evaluations using the StereoMIS dataset show that our method substantially enhances novel view synthesis quality while maintaining competitive pose accuracy.

Current ultrasound image synthesis techniques often fall short in semantic accuracy and physical realism or produce images with a significant domain gap. Ultra-NeRF addresses these issues by creating a Neural Field from reconstructed acoustic properties via pose-annotated B-mode images and shows that it can be used for novel view synthesis of B-mode images. While Ultra-NeRF generates plausible results, it lacks explainability in the acoustic parameter space. In this paper, we revisit neural fields for ultrasound and introduce the Sonographic Neural Reflection Field (SuRF), which adheres to the physical properties of acoustic ultrasound. By redesigning Ultra-NeRF’s differentiable forward synthesis model and incorporating physics-inspired regularizations, we ensure the interpretability of learned acoustic parameters. Tested on the Ultra-NeRF in-silico dataset and a new multi-view ex-vivo 3D ultrasound dataset, our method demonstrates enhanced reconstruction and interpretation across various tissue types, including fat, muscle, and bone.

In this paper, we propose a novel encoder-decoder architecture, named SABER, to learn the 6D pose of the object in the embedding space by learning shape representation at a given pose. This model enables us to learn pose by performing shape representation at a target pose from RGB image input. We perform shape representation as an auxiliary task which helps us in learning rotations space for an object based on 2D images. An image encoder predicts the rotation in the embedding space and the DeepSDF based decoder learns to represent the object’s shape at the given pose. As our approach is shape based, the pipeline is suitable for any type of object irrespective of the symmetry. Moreover, we need only a CAD model of the objects to train SABER. Our pipeline is synthetic data based and can also handle symmetric objects without symmetry labels and, thus, no additional labeled training data is needed. The experimental evaluation shows that our method achieves close to benchmark results for both symmetric objects and asymmetric objects on Occlusion-LineMOD, and T-LESS datasets.

Category-level object pose estimation, aiming to predict the 6D pose and 3D size of objects from known categories, typically struggles with large intra-class shape variation. Existing works utilizing mean shapes often fall short of cap-turing this variation. To address this issue, we present Sec-ondPose, a novel approach integrating object-specific ge-ometric features with semantic category priors from DI-NOv2. Leveraging the advantage of DINOv2 in providing SE(3)-consistent semantic features, we hierarchically extract two types of SE(3)-invariant geometric features to further encapsulate local-to-global object-specific information. These geometric features are then point-aligned with DINOv2 features to establish a consistent object represen-tation under SE(3) transformations, facilitating the map-ping from camera space to the pre-defined canonical space, thus further enhancing pose estimation. Extensive exper-iments on NOCS-REAL275 demonstrate that SecondPose achieves a 12.4% leap forward over the state-of-the-art. Moreover, on a more complex dataset HouseCat6D which provides photometrically challenging objects, SecondPose still surpasses other competitors by a large margin.

Recent learning methods for object pose estimation require resource-intensive training for each individual object instance or category, hampering their scalability in real applications when confronted with previously unseen objects. In this paper, we propose MatchU, a Fuse-Describe-Match strategy for 6D pose estimation from RGB-D images. MatchU is a generic approach that fuses 2D texture and 3D geometric cues for 6D pose prediction of unseen objects. We rely on learning geometric 3D descriptors that are rotation-invariant by design. By encoding pose-agnostic geometry, the learned descriptors naturally generalize to unseen objects and capture symmetries. To tackle ambiguous associations using 3D geometry only, we fuse additional RGB information into our descriptor. This is achieved through a novel attention-based mechanism that fuses cross-modal information, together with a matching loss that leverages the latent space learned from RGB data to guide the descriptor learning process. Extensive experiments reveal the generalizability of both the RGB-D fusion strategy as well as the descriptor efficacy. Benefiting from the novel designs, MatchU surpasses all existing methods by a significant margin in terms of both accuracy and speed, even without the requirement of expensive re-training or rendering.

Estimating 6D object poses is a major challenge in 3D computer vision. Building on successful instance-level approaches, research is shifting towards category-level pose estimation for practical applications. Current category-level datasets, however, fall short in annotation quality and pose variety. Addressing this, we introduce HouseCat6D, a new category-level 6D pose dataset. It features 1) multi-modality with Polarimetric RGB and Depth (RGBD+P), 2) encompasses 194 diverse objects across 10 household cat-egories, including two photometrically challenging ones, and 3) provides high-quality pose annotations with an error range of only 1.35 mm to 1.74 mm. The dataset also includes 4) 41 large-scale scenes with comprehensive view-point and occlusion coverage,5) a checkerboard-free en-vironment, and 6) dense 6D parallel-jaw robotic grasp annotations. Additionally, we present benchmark results for leading category-level pose estimation networks.

Controllable scene synthesis aims to create interactive environments for numerous industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships in the scene graph while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to the lack of a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT, where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset are available on the website.

An outside-in system uses binocular stereo and a probabilistic sparse point cloud matcher to track objects with micrometre precision in real-time. Miniaturizing the system results in a markerless inside-out stereo method with improved rotational accuracy. Reducing the constraints, we reformulate marker-free monocular pose estimation as an action decision process where the next best pose is determined using a render-and-compare strategy. This allows instance agnostic pose estimation that generalizes to unseen objects. The methods are applied on a set of medical and industrial applications.