Felix Tristram

Ege Özsoy, Chantal Pellegrini, Tobias Czempiel et al.

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. Our code, and data is available at https://github.com/egeozsoy/MM-OR.

Felix Tristram, Stefano Gasperini, Benjamin Killeen et al.

The increasing maturity of embodied AI platforms has driven a growing interest in procedural video representation learning to support intelligent assistance systems for complex, multi-step tasks. Leveraging large-scale latent predictive training, video foundation models capture video dynamics, enabling downstream tasks such as activity understanding, spatiotemporal localization, and predictive control. However, procedural videos include actions with long-range dependencies that these models do not support, due to the quadratic complexity of self-attention. Distinct actions, for example, may be visually similar despite appearing at different points in the procedure, such as turning the stove on versus off. Here, we propose a backbone-agnostic approach that learns long-duration video representations by reducing the problem to a dense, frame-aligned action space and predicting pooled masked latent vectors. This approach allows our Procedural Joint Embedding Predictive Architecture (P-JEPA) to ingest videos over 30 minutes long, enabling effective long-form understanding of procedural steps. We evaluate P-JEPA using features extracted with VJEPA2.1, TSM, and I3D over the EgoExo4D, EgoProceL, and Assembly101 datasets, finding that it consistently improves linear separability, streaming inference, and temporal action segmentation performance, achieving state-of-the-art results on EgoExo4D fine-grained action classification while using an order of magnitude fewer parameters than LLM-based methods and running in real time.

Felix Tristram, Ege Özsoy, Christian Benz et al.

Fine-grained understanding of operating room (OR) activity could enable workflow-aware assistance, yet remains difficult due to clutter, occlusions, and limited sensing. The prevailing approach to model this environment is scene graphs as an interpretable representation of OR interactions. Converting their frame-wise relational predictions into temporally extended, fine-grained actions however, is challenging without explicit temporal modeling. To enable a principled temporal evaluation of current OR understanding methods, we introduce the first action-centric benchmark built on a publicly available ego-exocentric OR dataset by defining a fine-grained, multi-role action taxonomy and generating dense action segments via distillation from ground-truth scene graph state changes. Experiments on this benchmark show that current scene graph prediction methods struggle to model temporal structure, even when adding explicit modeling through Graph Neural Networks. We therefore introduce a vision-only temporal model that outperforms graph-based methods significantly when using all available egocentric video as input. Building on this model we also introduce a novel multi- to single-view feature alignment strategy that improves single-view performance on multi-role action recognition, mitigating the need for extensive egocentric video capture. Benchmark and code will be released upon acceptance.

Ege Özsoy, Arda Mamur, Felix Tristram et al.

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.

Florian Philipp Stilz, Mert Asim Karaoglu, Felix Tristram et al.

Reconstruction of endoscopic scenes is an important asset for various medical applications, from post-surgery analysis to educational training. Neural rendering has recently shown promising results in endoscopic reconstruction with deforming tissue. However, the setup has been restricted to a static endoscope, limited deformation, or required an external tracking device to retrieve camera pose information of the endoscopic camera. With FLex we adress the challenging setup of a moving endoscope within a highly dynamic environment of deforming tissue. We propose an implicit scene separation into multiple overlapping 4D neural radiance fields (NeRFs) and a progressive optimization scheme jointly optimizing for reconstruction and camera poses from scratch. This improves the ease-of-use and allows to scale reconstruction capabilities in time to process surgical videos of 5,000 frames and more; an improvement of more than ten times compared to the state of the art while being agnostic to external tracking information. Extensive evaluations on the StereoMIS dataset show that FLex significantly improves the quality of novel view synthesis while maintaining competitive pose accuracy.

Felix Tristram, Stefano Gasperini, Nassir Navab et al.

Recent neural rendering and reconstruction techniques, such as NeRFs or Gaussian Splatting, have shown remarkable novel view synthesis capabilities but require hundreds of images of the scene from diverse viewpoints to render high-quality novel views. With fewer images available, these methods start to fail since they can no longer correctly triangulate the underlying 3D geometry and converge to a non-optimal solution. These failures can manifest as floaters or blurry renderings in sparsely observed areas of the scene. In this paper, we propose Re-Nerfing, a simple and general add-on approach that leverages novel view synthesis itself to tackle this problem. Using an already trained NVS method, we render novel views between existing ones and augment the training data to optimize a second model. This introduces additional multi-view constraints and allows the second model to converge to a better solution. With Re-Nerfing we achieve significant improvements upon multiple pipelines based on NeRF and Gaussian-Splatting in sparse view settings of the mip-NeRF 360 and LLFF datasets. Notably, Re-Nerfing does not require prior knowledge or extra supervision signals, making it a flexible and practical add-on.