EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder

Bowen Chai; Tianbao Zhang; Shuyu Wu; Dexin Zuo; Zhaoxin Fan; Danping Zou

cs.CVOct 3, 2026

EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder

Authors: Bowen Chai, Tianbao Zhang, Shuyu Wu, Dexin Zuo, Zhaoxin Fan, Danping Zou

Organizations: Shanghai Jiao Tong University · Beihang University

Abstract

Recovering detailed geometry from high-resolution images is critical for precise perception of the surroundings and objects. However, existing methods which use latent-space modeling and VAE reconstruction can compromise geometric details. Furthermore, decoding from latent codes introduces substantial inference overhead. To address those issues, we present EagleDepth, an efficient framework for high-resolution monocular depth estimation that combines the geometric priors of latent diffusion with fine-grained pixel-space generation. Our key idea is to retain depth-aware latent representations as guidance while generating the final depth map directly in pixel space. We train the latent and pixel components sequentially: first, we fine-tune a pretrained latent diffusion model using paired RGB--depth supervision; then, we adapt a pretrained pixel diffusion decoder, PiD, to predict depth conditioned on the learned features. Training of the pixel component starts at 1024 resolution and continues across multiple resolutions up to 4K. The latent branch processes resized, lower-resolution RGB images, while the pixel branch generates depth at the target resolution, bypassing the original VAE decoder. This design preserves learned geometric knowledge without requiring the latent backbone to operate at the output resolution. On five commonly used depth estimation datasets and the high-resolution Synth4K dataset, our framework achieves state-of-the-art depth estimation performance, with faster inference and better preservation of fine structures and object boundaries.

Figures & tables

Figure 1: EagleDepth excels at predicting fine-grained depth maps from high-resolution images. Compared with state-of-the-art methods, our model achieves better depth estimation results with faster inference, as shown in the radar chart (quality metrics averaged over the five Synth4K ( Yu et al., 2026a ) subsets; larger radii indicate better performance)

Figure 2: Method overview. (a) An adapted latent predictor, trained with a pixel-space loss, estimates a coarse depth latent from a downsampled RGB image. (b) Conditioned on this latent, the pixel diffusion decoder generates a high-resolution depth map with fine-grained details. (c) A lightweight continuity-promoting module mitigates discontinuity artifacts at patch boundaries.

Figure 3: Qualitative comparison with leading monocular depth estimation methods. Our method preserves fine geometric details and thin structures while maintaining sharp depth boundaries and smooth surfaces, as highlighted by the arrows and zoomed-in regions.

Method	NYUv2		KITTI		ETH3D		ScanNet		DIODE
Method	AbsRel $\downarrow$	$\delta_{1}\uparrow$	AbsRel $\downarrow$	$\delta_{1}\uparrow$	AbsRel $\downarrow$	$\delta_{1}\uparrow$	AbsRel $\downarrow$	$\delta_{1}\uparrow$	AbsRel $\downarrow$	$\delta_{1}\uparrow$
MiDaS	11.1	88.5	23.6	63.0	18.4	75.2	12.1	84.6	—	—
DA2	4.5	97.9	7.4	94.6	13.1	86.5	6.5	97.2	6.6	95.2
Marigold	5.5	96.4	9.9	91.6	6.5	96.0	6.4	95.1	10.0	90.7
Lotus-2	5.0	97.6	6.6	95.7	5.1	97.5	5.2	97.3	6.1	95.2
DA3	4.1	98.0	5.9	97.2	4.4	97.8	3.9	97.9	5.9	95.1

Table 1: Quantitative results on standard depth benchmarks. Bold and underlined values denote the best and second-best results, respectively. Our method achieves the best results on four of the five benchmarks and remains competitive on KITTI.

	Method	Synth4K-1		Synth4K-2		Synth4K-3		Synth4K-4		Synth4K-5
	Method	AbsRel $\downarrow$	$\delta_{1}\uparrow$	AbsRel $\downarrow$	$\delta_{1}\uparrow$	AbsRel $\downarrow$	$\delta_{1}\uparrow$	AbsRel $\downarrow$	$\delta_{1}\uparrow$	AbsRel $\downarrow$	$\delta_{1}\uparrow$
Overall	DA3	38.3	45.7	29.7	51.2	32.2	53.2	23.7	63.9	23.8	58.9
	MoGe-2	22.1	67.1	16.6	76.6	18.0	79.3	14.1	82.9	11.0	85.9
	PPD	15.9	79.4	11.7	87.3	12.7	87.7	11.9	88.2	9.1	93.1
	PointDiT	44.2	42.6	40.4	40.2	47.7	36.6	29.6	55.6	39.1	38.4
	URGT	15.0	81.1	10.6	87.5	15.3	84.9	7.4	94.0	7.6	92.6

Table 2: Depth accuracy on the high-resolution Synth4K benchmark, evaluated over the full valid region (Overall) and high-frequency regions. Results for InfiniDepth † are reported with a

504\times 896

input and a 4K output, following its original paper. All other results are reported with 4K inputs and outputs. Our method demonstrates leading performance at high resolution.

Method	Synth4K-1	Synth4K-2	Synth4K-3	Synth4K-4	Synth4K-5
DA3	8.7	10.8	9.2	11.1	14.1
MoGe-2	15.7	13.1	13.2	14.9	18.2
PPD	15.0	18.4	15.8	18.7	16.1
PointDiT	20.7	21.8	17.4	22.1	20.1
URGT	20.9	16.0	15.0	18.2	21.4
InfiniDepth	15.7	20.0	13.1	23.6	21.7

Table 3: Boundary F1

\uparrow

(radius = 1) results on Synth4K. Our multi-resolution model achieves the highest scores across all five subsets, demonstrating excellent depth boundary quality.

Figure 4: Ablation study of the proposed continuity-promoting module. The module effectively mitigates discontinuity artifacts between patches.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Depth resolution	Selection	Samples
Hypersim	$768\times 1024$	AnyDepth filtering	26,695
VKITTI2	$375\times 1242$	AnyDepth filtering	12,643
TartanAir	$480\times 640$	AnyDepth filtering	186,693
IRS	$540\times 960$	AnyDepth filtering	68,211
EDEN	$480\times 640$	Official subset	12,520
RobbyReal	$480\times 640$ , $720\times 1280$	Every tenth frame	139,575

Appendix

Table 7: Training datasets and sample selection strategies. We report depth resolutions (

H\times W

), selection criteria, and the number of selected RGB–depth pairs for each dataset.

Figure 5: Point cloud results of our method.

Component	$512\times 512$		$1024\times 1024$		$2048\times 2048$		$2160\times 3840$
Component	Time	Memory	Time	Memory	Time	Memory	Time	Memory
VAE Encoder	16	11.9	83	13.2	424	18.0	1058	24.4
DiT	102	11.8	349	12.4	1733	14.7	4423	17.6
VAE Decoder	34	12.1	159	13.8	732	20.7	1668	29.8
Pixel Diffusion	37	11.8	78	12.4	487	14.8	1298	18.0
CPM	2	11.7	7	11.9	39	13.1	77	14.7

Appendix

Table 9: Component-wise runtime (ms

\downarrow

) and peak GPU memory (GB

\downarrow

) analysis. All runtime results are evaluated on an NVIDIA RTX 4090 GPU. CPM denotes the continuity-promoting module.

Figure 6: More visual results (1). Zoom in for better visibility.

Figure 7: More visual results (2). Zoom in for better visibility.

Figure 8: More visual results (3). Zoom in for better visibility.

Depth Estimation

Depth estimation infers scene distance from images and sensors, enabling 3D reconstruction, navigation, and spatial understanding.

See all 198 papers

Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention
Aug 31, 2026Bingde Liu, Wu Ran, Jinglei Zhang +2Monocular Depth Estimation Pixel-Space Diffusion Models
MoE Key Lab of Artificial Intelligence, Institute of AI, Shanghai Jiao Tong University, Shanghai, China · Zhiyuan College, Shanghai Jiao Tong University, Shanghai, China
PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation
Aug 17, 2026Zhiyuan Yuan, Guanying Chen, Lingteng Qiu +3Depth Estimation Vision Transformer
1Sun Yat-sen University · 3CUHKSZ · 2Shenzhen-FNii
DVD: Deterministic Video Depth Estimation with Generative Priors
Mar 12, 2026Hongfei Zhang, Harold Haodong Chen, Chenfei Liao +12Video Depth Estimation Depth Estimation
HKUST(GZ) · HKUST · UCSD +5

Aug 31, 2026J/K move · Enter open · S save

Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention

Bingde Liu, Wu Ran, Jinglei Zhang, Huanhuan Yuan+1

MoE Key Lab of Artificial Intelligence, Institute of AI, Shanghai Jiao Tong University, Shanghai, China · Zhiyuan College, Shanghai Jiao Tong University, Shanghai, China

Monocular Depth Estimation Pixel-Space Diffusion Models Few-Step Diffusion Sampling Diffusion Model Inference Acceleration

Open paper AskPDF arXiv

This work presents

\textbf{Lapis}

, a

\textbf{l}

inear-

\textbf{a}

ttention-based

\textbf{pi}

xel-

\textbf{s}

pace generative framework that achieves efficient and high-fidelity depth estimation with one-step diffusion. While generative frameworks have significantly advanced monocular depth estimation with superior detail fidelity, the

\mathcal{O}(N^2)

complexity of standard attention and the multi-step denoising process introduce prohibitive computational costs when scaling them to high-resolution image applications. Although linear attention and one-step prediction are intuitively viable, directly applying them leads to poor structural consistency, detail loss, and noise. Lapis rectifies these limitations through a coarse-to-fine hierarchy. Specifically, a Patch-level Consistency Module restores structural coherence by integrating semantic and spatial priors. Subsequently, a Pixel-level Refinement Module recovers sharp geometric boundaries via skip-connection-based pixel correspondence. Furthermore, to mitigate sampling noise inherent in one-step diffusion, we leverage the manifold assumption and adopt a direct

\mathbf{x}

-prediction strategy to target the clean data manifold. Extensive evaluations on multiple benchmarks demonstrate that Lapis consistently achieves state-of-the-art (SOTA) accuracy and boundary sharpness across various resolutions, reducing inference latency by up to 7.6

\times

at 1080P and 10.9

\times

at 1440P resolution compared to previous SOTA generative models.

Abstract

Depth Estimation

Explore similar work

Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention

PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation

DVD: Deterministic Video Depth Estimation with Generative Priors