Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching

• URL: http://arxiv.org/abs/2604.18623v1
• Date: Sat, 18 Apr 2026 01:48:43 GMT
• Title: Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching
• Abstract summary: Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples.<n>We propose FlowSG, which recasts SGG as continuous-time transport on a hybrid discrete-continuous state.<n>Experiments on VG and PSG under closed- and open-vocabulary protocols show consistent gains in predicate R/mR and graph-level metrics.
• Score: 35.40374108008262
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, deterministic classification problem rather than a genuinely progressive, generative task. We propose FlowSG, which recasts SGG as continuous-time transport on a hybrid discrete-continuous state: starting from a noised graph, the model progressively grows an image-conditioned scene graph through constraint-aware refinements that jointly synthesize nodes (objects) and edges (predicates). Specifically, we first leverage a VQ-VAE to quantize a scene graph (e.g., continuous visual features) into compact, predictable tokens; a graph Transformer then (i) predicts a conditional velocity field to transport continuous geometry (boxes) and (ii) updates discrete posteriors for categorical tokens (object features and predicate labels), coupling semantics and geometry via flow-conditioned message aggregation. Training combines flow-matching losses for geometry with a discrete-flow objective for tokens, yielding few-step inference and plug-and-play compatibility with standard detectors and segmenters. Extensive experiments on VG and PSG under closed- and open-vocabulary protocols show consistent gains in predicate R/mR and graph-level metrics, validating the mixed discrete-continuous generative formulation over one-shot classification baselines, with an average improvement of about 3 points over the state-of-the-art USG-Par.

Related papers

• SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generation [44.62000477544674]
  We propose SGFormer++, a novel Semantic Graph Transformer for 3D scene graph generation (SGG)<n>It parses point cloud scenes into semantic structural graphs, where nodes denote detected object instances and edges encode their pairwise relationships.<n>It achieves state-of-the-art performance in both standard and incremental settings.
  arXiv  Detail & Related papers  (2026-06-13T14:41:56Z)
• Scalable Graph Generative Modeling via Substructure Sequences [50.32639806800683]
  We introduce Generative Graph Pattern Machine (G$2$PM), a generative Transformer pre-training framework for graphs.<n>G$2$PM represents graph instances (nodes, edges, or entire graphs) as sequences of substructures.<n>It employs generative pre-training over the sequences to learn generalizable and transferable representations.
  arXiv  Detail & Related papers  (2025-05-22T02:16:34Z)
• PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks [51.31903029903904]
  In Scene Graphs Generation (SGG) one extracts structured representation from visual inputs in the form of objects nodes and predicates connecting them.<n> PRISM-0 is a framework for zero-shot open-vocabulary SGG that bootstraps foundation models in a bottom-up approach.<n> PRIMS-0 generates semantically meaningful graphs that improve downstream tasks such as Image Captioning and Sentence-to-Graph Retrieval.
  arXiv  Detail & Related papers  (2025-04-01T14:29:51Z)
• DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation [61.59996525424585]
  DIFFVSGG is an online VSGG solution that frames this task as an iterative scene graph update problem.<n>We unify the decoding of object classification, bounding box regression, and graph generation three tasks using one shared feature embedding.<n>DIFFVSGG further facilitates continuous temporal reasoning, where predictions for subsequent frames leverage results of past frames as the conditional inputs of LDMs.
  arXiv  Detail & Related papers  (2025-03-18T06:49:51Z)
• Open-Vocabulary Octree-Graph for 3D Scene Understanding [54.11828083068082]
  Octree-Graph is a novel scene representation for open-vocabulary 3D scene understanding. An adaptive-octree structure is developed that stores semantics and depicts the occupancy of an object adjustably according to its shape.
  arXiv  Detail & Related papers  (2024-11-25T10:14:10Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Self-Supervised Relation Alignment for Scene Graph Generation [44.3983804479146]
  We introduce a self-supervised relational alignment regularization to improve scene graph generation performance. The proposed alignment is general and can be combined with any existing scene graph generation framework. We illustrate the effectiveness of this self-supervised relational alignment in conjunction with two scene graph generation architectures.
  arXiv  Detail & Related papers  (2023-02-02T20:34:13Z)
• SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation [4.319987790757823]
  Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding and visual understanding tasks. Due to the long tail bias problem of the object and predicate labels in the available annotated data, the scene graph generated from current methodologies can be biased toward common, non-informative relationship labels. In this work, we proposed the SG-Shuffle pipeline for scene graph generation with 3 components: 1) Parallel Transformer, which learns to predict object relationships in a more exclusive manner by grouping relationship labels into groups of similar purpose; 2) Shuffle Transformer, which learns to select the final relationship labels from the category-specific feature
  arXiv  Detail & Related papers  (2022-11-09T10:00:45Z)
• Iterative Scene Graph Generation [55.893695946885174]
  Scene graph generation involves identifying object entities and their corresponding interaction predicates in a given image (or video) Existing approaches to scene graph generation assume certain factorization of the joint distribution to make the estimation iteration feasible. We propose a novel framework that addresses this limitation, as well as introduces dynamic conditioning on the image.
  arXiv  Detail & Related papers  (2022-07-27T10:37:29Z)
• Panoptic Scene Graph Generation [41.534209967051645]
  panoptic scene graph generation (PSG) is a new problem task that requires the model to generate a more comprehensive scene graph representation. A high-quality PSG dataset contains 49k well-annotated overlapping images from COCO and Visual Genome.
  arXiv  Detail & Related papers  (2022-07-22T17:59:53Z)
• SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection [26.0630601028093]
  Domain Adaptive Object Detection (DAOD) leverages a labeled domain to learn an object detector generalizing to a novel domain free of annotations. Recent advances align class-conditional distributions by narrowing down cross-domain prototypes (class centers) We propose a novel SemantIc-complete Graph MAtching framework for hallucinationD, which completes mismatched semantics and reformulates the adaptation with graph matching.
  arXiv  Detail & Related papers  (2022-03-12T10:14:17Z)
• Fully Convolutional Scene Graph Generation [30.194961716870186]
  This paper presents a fully convolutional scene graph generation (FCSGG) model that detects objects and relations simultaneously. FCSGG encodes objects as bounding box center points, and relationships as 2D vector fields which are named as Relation Affinity Fields (RAFs) FCSGG achieves highly competitive results on recall and zero-shot recall with significantly reduced inference time.
  arXiv  Detail & Related papers  (2021-03-30T05:25:38Z)

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.