# SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning

arXiv: https://arxiv.org/abs/2507.05798 · HTML: https://mlsanity.com/paper/2507.05798/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 2 of its 69 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 2 of 2)

- [Graph Transformers: A Survey](https://mlsanity.com/paper/2407.09777/) (2024)
- [Semantic Compositional Learning for Low-shot Scene Graph Generation](https://mlsanity.com/paper/2108.08600/) (2021)

## Built on by (most cited first, 10 of 10)

- [Graph is a Substrate Across Data Modalities](https://mlsanity.com/paper/2601.22384/) (2026)
- [TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition](https://mlsanity.com/paper/2511.15085/) (2025)
- [ScriptHOI: Learning Scripted State Transitions for Open-Vocabulary Human-Object Interaction Detection](https://mlsanity.com/paper/2605.05057/) (2026)
- [Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching](https://mlsanity.com/paper/2604.18623/) (2026)
- [CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation](https://mlsanity.com/paper/2604.22274/) (2026)
- [ReLIC-SGG: Relation Lattice Completion for Open-Vocabulary Scene Graph Generation](https://mlsanity.com/paper/2604.22546/) (2026)
- [RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnesses](https://mlsanity.com/paper/2605.20823/) (2026)
- [Resolving Ambiguity in Composed Image Retrieval via Calibrated Interaction](https://mlsanity.com/paper/2605.24634/) (2026)
- [Show, Don't Ask: Generative Visual Disambiguation for Composed Image Retrieval with Turn-Valid Coverage](https://mlsanity.com/paper/2606.18992/) (2026)
- [GHOST: Geometry-Constrained Hybrid Diffusion for Open-Vocabulary 3D Scene Graph Generation](https://mlsanity.com/paper/2610.16455/) (2026)

## Abstract (arXiv)

Panoptic Scene Graph Generation (PSG) integrates instance segmentation with relation understanding to capture pixel-level structural relationships in complex scenes. Although recent approaches leveraging pre-trained vision-language models (VLMs) have significantly improved performance in the open-vocabulary setting, they commonly ignore the inherent limitations of VLMs in spatial relation reasoning, such as difficulty in distinguishing object relative positions, which results in suboptimal relation prediction. Motivated by the denoising diffusion model's inversion process in preserving the spatial structure of input images, we propose SPADE (SPatial-Aware Denoising-nEtwork) framework -- a novel approach for open-vocabulary PSG. SPADE consists of two key steps: (1) inversion-guided calibration for the UNet adaptation, and (2) spatial-aware context reasoning. In the first step, we calibrate a general pre-trained teacher diffusion model into a PSG-specific denoising network with cross-attention maps derived during inversion through a lightweight LoRA-based fine-tuning strategy. In the second step, we develop a spatial-aware relation graph transformer that captures both local and long-range contextual information, facilitating the generation of high-quality relation queries. Extensive experiments on benchmark PSG and Visual Genome datasets demonstrate that SPADE outperforms state-of-the-art methods in both closed- and open-set scenarios, particularly for spatial relationship prediction.