Deep learning-based light field occlusion removal: a comparative study

Light field (LF) occlusion removal aims to reconstruct scene content occluded by foreground objects by exploiting the multi-view redundancy of sub-aperture images (SAIs). This paper presents a comprehensive comparative study of LF occlusion-removal methods, organized into six methodological families: one covering traditional signal-processing approaches and five deep-learning paradigms, including implicit single-branch reconstruction, explicit dual-branch mask-guided networks with hard binary masks, dual-branch architectures with soft or adaptive confidence masks, representation-based methods using multi-plane images (MPI) or macro-pixel images (MacPI), and hybrid frameworks integrating LFs with vision-language model (VLM) priors. We first establish a unified taxonomy encompassing these architectural families. We then provide consolidated benchmark comparisons under two widely adopted evaluation protocols, analyze reproducibility variations in repeatedly reported baseline results, and investigate the trade-offs among reconstruction accuracy, model complexity, and inference efficiency using parameter count, FLOPs, and latency. Furthermore, we examine the evolution of LF occlusion-removal architectures from the perspectives of masking strategies, scene representations, backbone design, and loss functions. Our analysis indicates that soft confidence-guided masking combined with MPI- or MacPI-based representations achieves the highest self-reported reconstruction quality under the DeOccNet protocol. However, this pattern is not consistent across protocols: under the independently reported ISTY protocol, the top-performing method instead employs an implicit single-branch backbone without explicit masking or an MPI/MacPI representation, suggesting that backbone design may be as influential as masking strategy and representation choice. Lightweight networks with only 11–17M parameters nonetheless achieve accuracy comparable to substantially larger models. In contrast, VLM-guided reconstruction offers a fundamentally different training-free paradigm but remains limited by high inference latency and hallucination artifacts. Finally, we identify benchmark inconsistency, limited generalization to dense LFs, and controllable generative reconstruction as the primary research challenges and promising directions for future work.

Authors

Institutions

Publication Details

Journal
Artificial Intelligence Review
Published
2026-11-17
DOI
https://doi.org/10.1007/s10462-026-11738-9
Primary Topic
Advanced Vision and Imaging
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Deep learning-based light field occlusion removal: a comparative study

Mostafa Farouk Senussi, Asmaa Gamal Abdelbasset, Hyun-Soo Kang
3 links
Artificial Intelligence Review
Advanced Vision and Imaging
article

Deep learning-based light field occlusion removal: a comparative study

Mostafa Farouk Senussi, Asmaa Gamal Abdelbasset, Hyun-Soo Kang
article en

Abstract

Light field (LF) occlusion removal aims to reconstruct scene content occluded by foreground objects by exploiting the multi-view redundancy of sub-aperture images (SAIs). This paper presents a comprehensive comparative study of LF occlusion-removal methods, organized into six methodological families: one covering traditional signal-processing approaches and five deep-learning paradigms, including implicit single-branch reconstruction, explicit dual-branch mask-guided networks with hard binary masks, dual-branch architectures with soft or adaptive confidence masks, representation-based methods using multi-plane images (MPI) or macro-pixel images (MacPI), and hybrid frameworks integrating LFs with vision-language model (VLM) priors. We first establish a unified taxonomy encompassing these architectural families. We then provide consolidated benchmark comparisons under two widely adopted evaluation protocols, analyze reproducibility variations in repeatedly reported baseline results, and investigate the trade-offs among reconstruction accuracy, model complexity, and inference efficiency using parameter count, FLOPs, and latency. Furthermore, we examine the evolution of LF occlusion-removal architectures from the perspectives of masking strategies, scene representations, backbone design, and loss functions. Our analysis indicates that soft confidence-guided masking combined with MPI- or MacPI-based representations achieves the highest self-reported reconstruction quality under the DeOccNet protocol. However, this pattern is not consistent across protocols: under the independently reported ISTY protocol, the top-performing method instead employs an implicit single-branch backbone without explicit masking or an MPI/MacPI representation, suggesting that backbone design may be as influential as masking strategy and representation choice. Lightweight networks with only 11–17M parameters nonetheless achieve accuracy comparable to substantially larger models. In contrast, VLM-guided reconstruction offers a fundamentally different training-free paradigm but remains limited by high inference latency and hallucination artifacts. Finally, we identify benchmark inconsistency, limited generalization to dense LFs, and controllable generative reconstruction as the primary research challenges and promising directions for future work.

Artificial Intelligence Review
Chungbuk National University (KR), Assiut University (EG)
Advanced Vision and Imaging
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon