# Vision-Reasoning-Guided Occlusion Removal from Light Fields

arXiv: https://arxiv.org/abs/2606.19985 · HTML: https://mlsanity.com/paper/2606.19985/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 48 of its 86 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 30 of 48)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [Semantic Image Inpainting with Deep Generative Models](https://mlsanity.com/paper/1607.07539/) (2016)
- [Focal Sparse Convolutional Networks for 3D Object Detection](https://mlsanity.com/paper/2204.12463/) (2022)
- [Recurrent Feature Reasoning for Image Inpainting](https://mlsanity.com/paper/2008.03737/) (2020)
- [High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis](https://mlsanity.com/paper/1611.09969/) (2016)
- [Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding](https://mlsanity.com/paper/2203.00867/) (2022)
- [Image Inpainting via Conditional Texture and Structure Dual Generation](https://mlsanity.com/paper/2108.09760/) (2021)
- [Image Inpainting with Learnable Bidirectional Attention Maps](https://mlsanity.com/paper/1909.00968/) (2019)
- [GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation](https://mlsanity.com/paper/2504.02782/) (2025)
- [Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers](https://mlsanity.com/paper/2510.07316/) (2025)
- [CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying](https://mlsanity.com/paper/2303.08524/) (2023)
- [An Autonomous Drone for Search and Rescue in Forests using Airborne Optical Sectioning](https://mlsanity.com/paper/2105.04328/) (2021)
- [Unified Transformer Tracker for Object Tracking](https://mlsanity.com/paper/2203.15175/) (2022)
- [Search and Rescue with Airborne Optical Sectioning](https://mlsanity.com/paper/2009.08835/) (2020)
- [Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets](https://mlsanity.com/paper/2512.15110/) (2025)
- [A Statistical View on Synthetic Aperture Imaging for Occlusion Removal](https://mlsanity.com/paper/1906.06600/) (2019)
- [Learning Prior Feature and Attention Enhanced Image Inpainting](https://mlsanity.com/paper/2208.01837/) (2022)

## Abstract (arXiv)

Occlusion-robust scene recovery remains a major challenge in computational imaging, particularly where dense vegetation severely limits visibility. We propose a visionreasoning-guided light field occlusion removal framework combining light field integration (LFI) with vision-language model (VLM) semantic reasoning. Multi-view observations are first integrated via LFI to suppress foreground occlusions, producing an initial visibility-enhanced representation, a VLM then acts as a conditional semantic prior to restore degraded structures and fine details. A multi-sample fusion strategy aggregates multiple generated hypotheses to improve consistency and reduce hallucination. Experimental results on synthetic and real-world datasets show state-of-the-art performance, achieving the highest average SSIM across four synthetic benchmark scenes (4-Syn) and strong generalization across structured and unstructured acquisition settings, with applicability to search-and-rescue and exploratory robotic navigation.