S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR

• URL: http://arxiv.org/abs/2402.14461v2
• Date: Wed, 7 Aug 2024 06:01:18 GMT
• Title: S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR
• Authors: Jialun Pei, Diandian Guo, Jingyang Zhang, Manxi Lin, Yueming Jin, Pheng-Ann Heng,
• Abstract summary: Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
• Score: 50.435592120607815
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR). However, previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. This pipeline may potentially compromise the flexibility of learning multimodal representations, consequently constraining the overall effectiveness. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S^2Former-OR, aimed to complementally leverage multi-view 2D scenes and 3D point clouds for SGG in an end-to-end manner. Concretely, our model embraces a View-Sync Transfusion scheme to encourage multi-view visual information interaction. Concurrently, a Geometry-Visual Cohesion operation is designed to integrate the synergic 2D semantic features into 3D point cloud features. Moreover, based on the augmented feature, we propose a novel relation-sensitive transformer decoder that embeds dynamic entity-pair queries and relational trait priors, which enables the direct prediction of entity-pair relations for graph generation without intermediate steps. Extensive experiments have validated the superior SGG performance and lower computational cost of S^2Former-OR on 4D-OR benchmark, compared with current OR-SGG methods, e.g., 3 percentage points Precision increase and 24.2M reduction in model parameters. We further compared our method with generic single-stage SGG methods with broader metrics for a comprehensive evaluation, with consistently better performance achieved.

Related papers

• HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting [47.67153284714988]
  We propose a novel hybrid representation, termed as HybridGS, using 2D Gaussians for transient objects per image. We also propose a straightforward yet effective multi-stage training strategy to ensure robust training and high-quality view synthesis. Experiments on benchmark datasets show our state-of-the-art performance of novel view synthesis in both indoor and outdoor scenes.
  arXiv  Detail & Related papers  (2024-12-05T03:20:35Z)
• A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision [65.33043028101471]
  We introduce a diffusion model for Gaussian Splats, SplatDiffusion, to enable generation of three-dimensional structures from single images. Existing methods rely on deterministic, feed-forward predictions, which limit their ability to handle the inherent ambiguity of 3D inference from 2D data.
  arXiv  Detail & Related papers  (2024-12-01T00:29:57Z)
• Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding [59.51535163599723]
  FreeGS is an unsupervised semantic-embedded 3DGS framework that achieves view-consistent 3D scene understanding without the need for 2D labels. We show that FreeGS performs comparably to state-of-the-art methods while avoiding the complex data preprocessing workload.
  arXiv  Detail & Related papers  (2024-11-29T08:52:32Z)
• Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation [36.93661496405653]
  We take a global approach to exploit Transformer-temporal information with a concise Graph and Skipped Transformer architecture. Specifically, in 3D pose stage, coarse-grained body parts are deployed to construct a fully data-driven adaptive model. Experiments are conducted on Human3.6M, MPI-INF-3DHP and Human-Eva benchmarks.
  arXiv  Detail & Related papers  (2024-07-03T10:42:09Z)
• RT-GS2: Real-Time Generalizable Semantic Segmentation for 3D Gaussian Representations of Radiance Fields [6.071025178912125]
  We introduce RT-GS2, the first generalizable semantic segmentation method employing Gaussian Splatting. Our method achieves real-time performance of 27.03 FPS, marking an astonishing 901 times speedup compared to existing approaches.
  arXiv  Detail & Related papers  (2024-05-28T10:34:28Z)
• CLIP-GS: CLIP-Informed Gaussian Splatting for Real-time and View-consistent 3D Semantic Understanding [32.76277160013881]
  We present CLIP-GS, which integrates semantics from Contrastive Language-Image Pre-Training (CLIP) into Gaussian Splatting. SAC exploits the inherent unified semantics within objects to learn compact yet effective semantic representations of 3D Gaussians. We also introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model.
  arXiv  Detail & Related papers  (2024-04-22T15:01:32Z)
• Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection [116.21529970404653]
  We introduce SG2HOI+, a unified one-step model based on the Transformer architecture. Our approach employs two interactive hierarchical Transformers to seamlessly unify the tasks of SGG and HOI detection. Our approach achieves competitive performance when compared to state-of-the-art HOI methods.
  arXiv  Detail & Related papers  (2023-11-03T07:25:57Z)
• Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation [49.56131393810713]
  We present an SE(3) equivariant architecture and a training strategy to tackle this task in an unsupervised manner. Our method excels in both model performance and computational efficiency, with only 0.25M parameters and 0.92G FLOPs.
  arXiv  Detail & Related papers  (2023-06-08T22:55:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.