# Focusable Monocular Depth Estimation

arXiv: https://arxiv.org/abs/2605.11756 · HTML: https://mlsanity.com/paper/2605.11756/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 39 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 14 of 14)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding](https://mlsanity.com/paper/2507.00416/) (2025)
- [Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment](https://mlsanity.com/paper/2511.04555/) (2025)
- [Monocular Depth Estimation: A Survey](https://mlsanity.com/paper/1901.09402/) (2019)
- [Depth Anything with Any Prior](https://mlsanity.com/paper/2505.10565/) (2025)
- [EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark](https://mlsanity.com/paper/2510.06218/) (2025)
- [OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation](https://mlsanity.com/paper/2604.17876/) (2026)
- [OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer](https://mlsanity.com/paper/2603.14401/) (2026)

## Built on by (most cited first, 2 of 2)

- [LA4VLA: Learning to Act without Seeing via Language-Action Pretraining](https://mlsanity.com/paper/2606.27295/) (2026)
- [The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2608.04589/) (2026)

## Abstract (arXiv)

Monocular depth foundation models generalize well across scenes, yet they are typically optimized with uniform pixel-wise objectives that do not distinguish user-specified or task-relevant target regions from the surrounding context. We therefore introduce Focusable Monocular Depth Estimation (FDE), a region-aware depth estimation task in which, given a specified target region, the model is required to prioritize foreground depth accuracy, preserve sharp boundary transitions, and maintain coherent global scene geometry. To prioritize task-critical region modeling, we propose FocusDepth, a prompt-conditioned monocular relative depth estimation framework that guides depth modeling to focus on target regions via box/text prompts. The core Multi-Scale Spatial-Aligned Fusion (MSSA) in FocusDepth spatially aligns multi-scale features from Segment Anything Model 3 to the Depth Anything family and injects them through scale-specific, gated conditional fusion. This enables dense prompt cue injection without disrupting geometric representations, thereby endowing the depth estimation model with focused perception capability. To study FDE, we establish FDE-Bench, a target-centric monocular relative depth benchmark built from image-target-depth triplets across five datasets, containing 252.9K/72.5K train/val triplets and 972 categories spanning real-world and embodied simulation environments. On FDE-Bench, FocusDepth consistently improves over globally fine-tuned DA2/DA3 baselines under both box and text prompts, with the largest gains appearing in target boundary and foreground regions while preserving global scene geometry. Ablations show that MSSA's spatial alignment is the key design factor, as disrupting prompt-geometry correspondence increases AbsRel by up to 13.8%.