NemoSplat: Feed-Forward 4D Gaussian Splatting for Media-Aware Underwater Reconstruction

Xiaopeng Guo; Wai Chung Tse; Yipeng Zhu; Hanwen Zhang; Huajian Huang; Sai-Kit Yeung

cs.CVAug 24, 2026

NemoSplat: Feed-Forward 4D Gaussian Splatting for Media-Aware Underwater Reconstruction

Authors: Xiaopeng Guo, Wai Chung Tse, Yipeng Zhu, Hanwen Zhang, Huajian Huang, Sai-Kit Yeung

Organizations: The Hong Kong University of Science and Technology, China · Beijing Institute of Technology, China

Abstract

Reconstructing photorealistic scenes in unconstrained underwater environments remains challenging due to severe media-induced light scattering and unpredictable dynamic objects. Recent feed-forward visual foundation models have demonstrated remarkable capabilities in generalized novel view synthesis and tracking. However, when directly applied to aquatic videos, optical attenuation and motion interference fatally corrupt their feature aggregation, leading to severe tracking and reconstruction failures. To overcome these limitations, we present NemoSplat, the first feed-forward 4D Gaussian Splatting framework tailored for media-aware dynamic reconstruction directly from uncalibrated marine videos. Beyond providing robust estimations of camera poses and dense scene depth, we devise a Promptable Dynamic Disentangler that utilizes a confidence-aware fusion strategy of learned dynamic probabilities and optional semantic text priors, effectively isolating massive transient entities. Furthermore, to counteract visual degradation, a Media-Aware Gaussian Predictor is formulated to jointly estimate intrinsic 3D Gaussian attributes alongside physical media parameters, rendering pristine scene appearance in a single forward pass. Additionally, we introduce a large-scale underwater dataset with massive dynamic elements to facilitate training and evaluation. Extensive experiments on our dataset demonstrate that NemoSplat achieves state-of-the-art tracking accuracy and high-fidelity rendering. Homepage: https://nemosplat.hkustvgd.com

Figures & tables

Figure 1. We present NemoSplat, a novel feed-forward model that directly reconstructs photorealistic underwater scenes from uncalibrated image sequences, robustly handling numerous dynamic objects and water-induced degradation. A teaser image showing the main result and concept of the paper.

Figure 2. Overview of our NemoSplat framework. It leverages the Visual Geometry Transformer to extract robust spatiotemporal features from uncalibrated underwater sequences. Subsequently, a shared feature encoder feeds these representations into specialized decoders to jointly estimate camera poses, depth, dynamic semantic masks (optionally refined via grounded text prompts), water backscatter and attenuation parameters, and intrinsic 4D Gaussians. Overview figure.

Figure 3. Dynamic-Semantic Mask Generation. The Promptable Dynamic Disentangler ( $F_{M}$ ) refines the predicted dynamic mask via logit adjustment using an optional text prompt-guided semantic map, effectively revising a highly accurate mask for downstream 4D modeling. A technical flowchart showing the Dynamic-Semantic Mask Generation pipeline.

Figure 4. Examples sequences of our proposed evaluation dataset. It includes synthetic scenes with precise ground-truth annotations and diverse in-the-wild underwater sequences for comprehensive evaluation. Sampled frames and depth maps from the evaluation dataset.

Method	BoulderShore				Coral				Deepsea				Average
Metrics	ATE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	ATE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	ATE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	ATE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$
VGGT ( Wang et al., 2025a )	0.19	-	-	-	0.23	-	-	-	5.93	-	-	-	2.12	-	-	-
StreamVGGT ( Zhuo et al., 2025 )	0.40	-	-	-	0.79	-	-	-	5.01	-	-	-	2.06	-	-	-
WildGS-SLAM ( Zheng et al., 2025 )	0.12	18.80	0.60	0.45	4.97	17.01	0.55	0.52	0.81	29.86	0.81	0.35	1.96	21.89	0.65	0.44
Droid-W ( Li et al., 2026 )	0.11	20.04	0.71	0.44	4.65	18.56	0.58	0.56	0.78	31.93	0.83	0.30	1.85	23.51	0.71	0.43
YoNoSplat ( Ye et al., 2026 )	0.39	17.81	0.46	0.55	0.27	17.63	0.44	0.56	$\times$	$\times$	$\times$	$\times$	$\times$	$\times$	$\times$	$\times$

Table 1. Quantitative evaluation on synthetic sequences. Best results are bold , second best are underlined . “-” indicates that the method does not support rendering, and “

\times

” denotes failure due to out of memory. ATE is reported in meters.

Method	Metrics	01	02	03	04	05	06	07	08	09	10	11	12	13	14	Avg.
WildGS-SLAM ( Zheng et al., 2025 )	PSNR $\uparrow$	19.31	18.13	20.85	19.92	19.24	21.75	19.79	16.08	21.40	19.38	20.79	21.64	16.29	13.50	19.15
	SSIM $\uparrow$	0.56	0.65	0.74	0.62	0.52	0.74	0.62	0.42	0.68	0.49	0.69	0.78	0.58	0.37	0.60
	LPIPS $\downarrow$	0.50	0.52	0.38	0.37	0.44	0.42	0.44	0.50	0.35	0.36	0.28	0.25	0.41	0.58	0.41
Droid-W ( Li et al., 2026 )	PSNR $\uparrow$	20.59	19.83	18.61	18.73	17.77	20.50	17.05	16.71	18.43	19.05	17.90	21.05	13.20	14.32	18.12
	SSIM $\uparrow$	0.73	0.69	0.51	0.55	0.40	0.68	0.49	0.50	0.60	0.46	0.63	0.72	0.50	0.43	0.56
	LPIPS $\downarrow$	0.37	0.39	0.46	0.37	0.52	0.51	0.58	0.42	0.43	0.39	0.36	0.27	0.50	0.57	0.44

Table 2. Quantitative evaluation of novel view synthesis on 14 real-world aquatic sequences. We report PSNR, SSIM, and LPIPS metrics across all scenes alongside their overall averages. The best results are bold , and the second best are underlined .

Figure 5. Restored images on SeaThru-NeRF ( Levy et al., 2023 ) dataset. Our approach recovers more natural colors while preserving clearer details in distant regions. Figures showing restored images on SeaThru-NeRF dataset.

Figure 6. Qualitative comparison of novel view synthesis on highly degraded real-world aquatic sequences. While conventional feed-forward modules and SLAM-based baselines suffer from severe ghosting, topological blurring, and visual artifacts caused by unconstrained dynamic entities (e.g., schools of swimming fish), NemoSplat explicitly decouples transient motion from the static topology. This disentanglement enables the synthesis of crisp, temporally consistent, and artifact-free novel views. Figures showing rendering results of baseline models and NemoSplat.

Figure 7. Reconstruction results on real-world aquatic sequences. Our method disentangles static Gaussian models from dynamic underwater scenes, providing comprehensive outputs including RGB rendering images, depth maps and dynamic masks.

Explore similar work

Ocean4D: Generative Underwater 4D Reconstruction via Medium-Aware Video Diffusion
Jun 22, 2026Yuqiang Huang, Yuxi Wang, Junyu Dong +1Camera-Conditioned Video Generation 4D Reconstruction
Faculty of Information Science and Engineering, Ocean University of China · Institute of Automation, Chinese Academy of Sciences
AquaFlow: A Monocular Gaussian Splatting SLAM for Underwater Streaming Reconstruction
Aug 24, 2026Yingxiang Xu, Kerui Ren, Wenqi Guo +4Underwater 3D Reconstruction 3DGS SLAM
Zhejiang University · Shanghai AI Laboratory · Shanghai Jiao Tong University +3
Underwater360: Reconstructing Underwater Scenes from Panoramic Images with Omnidirectional Gaussian Splatting
May 26, 2026Jiangbei Hu, Weichao Song, Shibo Yu +83D Gaussian Splatting Underwater Imaging
School of Software, Dalian University of Technology · College of Computing and Data Science, Nanyang Technological University

Jun 22, 2026J/K move · Enter open · S save

Ocean4D: Generative Underwater 4D Reconstruction via Medium-Aware Video Diffusion

Yuqiang Huang, Yuxi Wang, Junyu Dong, Zhaoxiang Zhang

Faculty of Information Science and Engineering, Ocean University of China · Institute of Automation, Chinese Academy of Sciences

Camera-Conditioned Video Generation 4D Reconstruction Video Diffusion Models Underwater Imaging Dynamic Scene Reconstruction Underwater 3D Reconstruction

Open paper AskPDF arXiv

Underwater 4D reconstruction remains challenging due to the coupling between degraded light transport in participating media and dynamic water variations. Most existing Methods are developed under in-air assumptions and do not explicitly account for underwater absorption and backscatter. Additionally, near-static assumptions make these approaches sensitive to drifting particles and dynamic distractors , leading to unstable geometry and inconsistent cross-view results. To address these issues, we propose a generative framework for underwater 4D reconstruction, named Ocean4D, which is built on two complementary components. Specifically, 4D-GCC constructs 4D geometrically consistent conditioning with improved cross-frame coverage, while the Medium-Aware Block performs implicit medium-aware denoising in the latent diffusion process to stabilize underwater appearance under absorption and scattering. Given a monocular video and target cameras, our method generates videos along the target trajectories while preserving global structure and cross-view consistency. Extensive experiments on both dynamic and static underwater benchmarks demonstrate state-of-the-art performance on underwater reconstruction.

Abstract

Explore similar work

Ocean4D: Generative Underwater 4D Reconstruction via Medium-Aware Video Diffusion

AquaFlow: A Monocular Gaussian Splatting SLAM for Underwater Streaming Reconstruction

Underwater360: Reconstructing Underwater Scenes from Panoramic Images with Omnidirectional Gaussian Splatting