# DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction

arXiv: https://arxiv.org/abs/2510.07152 · HTML: https://mlsanity.com/paper/2510.07152/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2025.

## Built on by (most cited first, 11 of 11)

- [Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching](https://mlsanity.com/paper/2602.15827/) (2026)
- [Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids](https://mlsanity.com/paper/2601.07718/) (2026)
- [Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction](https://mlsanity.com/paper/2512.07464/) (2025)
- [TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour](https://mlsanity.com/paper/2602.02331/) (2026)
- [DeFM: Learning Foundation Representations from Depth for Robotics](https://mlsanity.com/paper/2601.18923/) (2026)
- [Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotion](https://mlsanity.com/paper/2606.00637/) (2026)
- [MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds](https://mlsanity.com/paper/2606.10288/) (2026)
- [DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models](https://mlsanity.com/paper/2609.29092/) (2026)
- [EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal](https://mlsanity.com/paper/2607.13472/) (2026)
- [CAP: Continuously Adaptive Perception-Blind Humanoid Locomotion via Learned Denoising](https://mlsanity.com/paper/2609.11553/) (2026)
- [Loco-Loco-RL: Low-Cost Terrain Mapping for Humanoid Locomotion with Reinforcement Learning](https://mlsanity.com/paper/2609.19041/) (2026)

## Abstract (arXiv)

Recent advancements in legged robot perceptive locomotion have shown promising progress. However, terrain-aware humanoid locomotion remains largely constrained to two paradigms: depth image-based end-to-end learning and elevation map-based methods. The former suffers from limited training efficiency and a significant sim-to-real gap in depth perception, while the latter depends heavily on multiple vision sensors and localization systems, resulting in latency and reduced robustness. To overcome these challenges, we propose a novel framework that tightly integrates three key components: (1) Terrain-Aware Locomotion Policy with a Blind Backbone, which leverages pre-trained elevation map-based perception to guide reinforcement learning with minimal visual input; (2) Multi-Modality Cross-Attention Transformer, which reconstructs structured terrain representations from noisy depth images; (3) Realistic Depth Images Synthetic Method, which employs self-occlusion-aware ray casting and noise-aware modeling to synthesize realistic depth observations, achieving over 30% reduction in terrain reconstruction error. This combination enables efficient policy training with limited data and hardware resources, while preserving critical terrain features essential for generalization. We validate our framework on a full-sized humanoid robot, demonstrating agile and adaptive locomotion across diverse and challenging terrains.