# WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views

arXiv: https://arxiv.org/abs/2605.11743 · HTML: https://mlsanity.com/paper/2605.11743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 23 of 23)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](https://mlsanity.com/paper/1805.10483/) (2018)
- [Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression](https://mlsanity.com/paper/1904.07399/) (2019)
- [Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild](https://mlsanity.com/paper/2003.03771/) (2020)
- [Agent Modelling under Partial Observability for Deep Reinforcement Learning](https://mlsanity.com/paper/2006.09447/) (2020)
- [Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning](https://mlsanity.com/paper/2203.06541/) (2022)
- [STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection](https://mlsanity.com/paper/2306.02763/) (2023)
- [ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment](https://mlsanity.com/paper/2109.05721/) (2021)
- [Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation](https://mlsanity.com/paper/1908.06440/) (2019)
- [Precise Facial Landmark Detection by Reference Heatmap Transformer](https://mlsanity.com/paper/2303.07840/) (2023)
- [HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap](https://mlsanity.com/paper/2104.03100/) (2021)
- [Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection](https://mlsanity.com/paper/2411.07167/) (2024)
- [POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search](https://mlsanity.com/paper/2410.09583/) (2024)

## Abstract (arXiv)

Learning latent representations that capture both semantic and spatial information is central to efficient spatio-semantic reasoning. However, many existing approaches rely on implicit latent structures combined with dense feature maps or task-specific heads, limiting computational efficiency and flexibility. We propose WorldComp2D, a novel lightweight representation learning framework that explicitly structures latent space geometry according to object identity and spatial proximity using multiscale local receptive fields. This framework consists of (i) a proximity-dependent encoder that maps a given observation into a spatio-semantic latent space and (ii) a localizer that infers the coordinates of objects in the input from the resulting spatio-semantic representation. Using facial landmark localization as a proof-of-concept, we show that, compared to SoTA lightweight models, WorldComp2D reduces the numbers of parameters and FLOPs by up to 4.0X and 2.2X, respectively, while maintaining real-time performance on CPU. These results demonstrate that explicitly structured latent spaces provide an efficient and general foundation for spatio-semantic reasoning. This framework is open-sourced at https://github.com/JinSeongmin/WorldComp2D.