# TDFNet: Tri-projection Deformable Fusion Network for Panoramic Salient Object Detection

arXiv: https://arxiv.org/abs/2608.25808 · HTML: https://mlsanity.com/paper/2608.25808/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 62 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [Salient Object Detection: A Discriminative Regional Feature Integration Approach](https://mlsanity.com/paper/1410.5926/) (2014)
- [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022)
- [Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence](https://mlsanity.com/paper/2012.04404/) (2020)
- [Boundary-Aware Segmentation Network for Mobile and Web Applications](https://mlsanity.com/paper/2101.04704/) (2021)
- [Distortion-adaptive Salient Object Detection in 360^circ Omnidirectional Images](https://mlsanity.com/paper/1909.04913/) (2019)
- [Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss](https://mlsanity.com/paper/1912.08393/) (2019)
- [Multi-Projection Fusion and Refinement Network for Salient Object Detection in 360deg Omnidirectional Image](https://mlsanity.com/paper/2212.12378/) (2022)
- [What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?](https://mlsanity.com/paper/2505.22129/) (2025)
- [Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspective](https://mlsanity.com/paper/2412.17297/) (2024)
- [Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views](https://mlsanity.com/paper/2503.24382/) (2025)
- [Saliency Prediction on Omnidirectional Images with Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1904.07080/) (2019)
- [A Fixation-based 360deg Benchmark Dataset for Salient Object Detection](https://mlsanity.com/paper/2001.07960/) (2020)
- [PSGait: Gait Recognition using Parsing Skeleton](https://mlsanity.com/paper/2503.12047/) (2025)
- [DAGait: Generalized Skeleton-Guided Data Alignment for Gait Recognition](https://mlsanity.com/paper/2503.18830/) (2025)
- [Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs](https://mlsanity.com/paper/2606.26387/) (2026)
- [Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correction](https://mlsanity.com/paper/2512.18813/) (2025)
- [TP-Seg: Task-Prototype Framework for Unified Medical Lesion Segmentation](https://mlsanity.com/paper/2604.00684/) (2026)
- [DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance](https://mlsanity.com/paper/2606.08906/) (2026)
- [Omnidirectional Image Quality Captioning: A Large-scale Database and A New Model](https://mlsanity.com/paper/2502.15271/) (2025)
- [Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective](https://mlsanity.com/paper/2603.02629/) (2026)
- [Saliency-aware End-to-end Learned Variable-Bitrate 360-degree Image Compression](https://mlsanity.com/paper/2402.08862/) (2024)
- [Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering](https://mlsanity.com/paper/2602.00621/) (2026)
- [Multi-Scale Estimation for Omni-Directional Saliency Maps Using Learnable Equator Bias](https://mlsanity.com/paper/2309.08139/) (2023)

## Built on by (most cited first, 1 of 1)

- [S2A:Semantic-to-Spatial Alignment for Alignment-Free RGB-T Salient Object Detection](https://mlsanity.com/paper/2609.27413/) (2026)

## Abstract (arXiv)

Recent years have witnessed the growing potential of panoramic salient object detection in robotic vision, virtual reality, and related applications. However, projecting spherical scenes onto 2D planes inevitably introduces geometric distortions, which fundamentally limit the effectiveness of existing projection-based methods. Specifically, Equirectangular Projection (ERP) suffers from severe polar stretching distortions, while cube map projection introduces discontinuities across cube-face boundaries, resulting in degraded feature discriminability and compromised geometric consistency. To address these limitations, we propose TDFNet, the first Tri-projection Deformable Fusion Network for panoramic salient object detection, exploiting complementary projection representations to alleviate geometric distortions and improve detection performance.Specifically, we design a cross-projection deformable attention (CDA) module that leverages spatial correspondences between different projections to construct geometry-aware sampling locations, guiding deformable attention for cross-projection contextual aggregation and enhancing robustness against projection-induced deformations. Furthermore, we introduce a latitude-guided fusion module, which utilizes spherical latitude priors to construct geometric confidence weights for adaptively balancing ERP and CMP features. Meanwhile, LGF incorporates distortion-reduced semantic references from Tangent Projection to achieve cross-projection feature refinement and spatial alignment.By constructing a three-branch encoding architecture based on ERP, CMP, and Tangent Projection, TDFNet simultaneously preserves global spatial continuity, local geometric details, and fine-grained boundary information.