Vision-Reasoning-Guided Occlusion Removal from Light Fields

• URL: http://arxiv.org/abs/2606.19985v1
• Date: Thu, 18 Jun 2026 09:24:55 GMT
• Title: Vision-Reasoning-Guided Occlusion Removal from Light Fields
• Abstract summary: Occlusion-robust scene recovery is a major challenge in computational imaging.<n>We propose a vision-reasoning-guided light field occlusion removal framework.<n>A conditional semantic prior to restore degraded structures and recover fine details, guided by the observed measurements.
• Score: 1.1458853556386797
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Occlusion-robust scene recovery remains a major challenge in computational imaging, particularly in natural environments where dense foreground vegetation severely limits visibility. We propose a vision-reasoning-guided light field occlusion removal framework that combines the visibility recovery capability of light field integration (LFI) with the semantic reasoning capacity of vision-language models (VLMs). Multi-view observations are first integrated via LFI to suppress foreground occlusions and produce an initial visibility-enhanced representation. A VLM is then incorporated as a conditional semantic prior to restore degraded structures and recover fine details, guided by the observed measurements. To improve recovery consistency and reduce hallucination artifacts, we introduce a multi-sample fusion strategy that aggregates multiple generated hypotheses into a unified estimate. Experimental results on synthetic and real-world datasets demonstrate state-of-the-art performance, achieving the highest average SSIM across four synthetic light field benchmark scenes (4-Syn) and strong generalization across structured and unstructured acquisition settings. These results highlight the effectiveness of combining physical imaging constraints with vision-language reasoning for robust perception under severe occlusion, with applicability to search-and-rescue and exploratory robotic navigation.

Related papers

• Hyperspectral Intrinsic Decomposition: Joint Recovery of Reflectance and Photometric Components for Non-Lambertian Scenes [29.51510553736925]
  Hyperspectral intrinsic decomposition (HID) aims to disentangle material-related spectral properties and photometric effects in hyperspectral images.<n>Most existing HID studies have been developed under Lambertian or near-Lambertian assumptions.<n>We develop a unified inversion paradigm that reformulates the recovery of four coupled reflectance and photometric components as the estimation of two spectral--spatial target variables.
  arXiv  Detail & Related papers  (2026-07-28T07:26:07Z)
• Multimodal Object Detection Under Sparse Forest-Canopy Occlusion [0.15469452301122175]
  This paper presents a multimodal proof-of-concept pipeline that integrates three complementary approaches.<n>A YOLOv5 detector is fine-tuned on the Teledyne FLIR thermal dataset and evaluated on thermal and fused imagery.<n>Results show that the tested terrestrial LiDAR configuration provides limited penetration for object-level detection.
  arXiv  Detail & Related papers  (2026-05-14T18:39:51Z)
• Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models [84.94288033791346]
  We conduct a detailed diagnostic analysis to unveil a pervasive issue: visual representation degradation in MLLMs.<n>We attribute this phenomenon to a visual sacrifice driven by the singular text-generation objective, where the model compromises its visual fidelity to optimize for answer generation.<n>We propose Predictive Regularization to force degraded intermediate features to predict initial visual features, thereby maintaining the inherent visual attributes of the MLLM's internal representations.
  arXiv  Detail & Related papers  (2026-03-21T13:10:37Z)
• RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations [12.753436440584409]
  Vision-based Retrieval-Augmented Generation (VisRAG) leverages vision-language models (VLMs) to jointly retrieve relevant visual documents and generate grounded answers based on multimodal evidence.<n>Existing VisRAG models degrade in performance when visual inputs suffer from distortions such as blur, noise, low light, or shadow, where semantic and degradation factors become entangled within pretrained visual encoders.<n>We introduce RobustVisRAG, a causality-guided dual-path framework that improves VisRAG robustness while preserving efficiency and zero-shot generalization.
  arXiv  Detail & Related papers  (2026-02-25T15:27:57Z)
• CrystaL: Spontaneous Emergence of Visual Latents in MLLMs [55.34169914483764]
  We propose CrystaL (Crystallized Latent Reasoning), a single-stage framework with two paths to process intact and corrupted images.<n>By explicitly aligning the attention patterns and prediction distributions across the two paths, CrystaL crystallizes latent representations into task-relevant visual semantics.<n>Experiments on perception-intensive benchmarks demonstrate that CrystaL consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-24T15:01:30Z)
• Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding [54.05243949024302]
  Existing robust MLLMs rely on implicit training/adaptation that focuses solely on visual encoder generalization.<n>We propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains.<n>Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity.
  arXiv  Detail & Related papers  (2025-12-19T12:56:17Z)
• RefLSM: Linearized Structural-Prior Reflectance Model for Medical Image Segmentation and Bias-Field Correction [10.716406019360441]
  We propose a novel variational Reflectance-based Level Set Model (RefLSM) for medical image segmentation.<n>RefLSM explicitly integrates Retinex-inspired reflectance decomposition into the segmentation framework.<n>We show that RefLSM achieves superior segmentation accuracy, robustness, and computational efficiency compared to state-of-the-art level set methods.
  arXiv  Detail & Related papers  (2025-12-08T06:06:29Z)
• INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifacts [0.0]
  Current forensic systems degrade sharply under real-world conditions.<n>Most detectors operate as opaques, offering little insight into why an image is flagged as synthetic.<n>We introduce INSIGHT, a unified framework for robust detection and transparent explanation of AI-generated images.
  arXiv  Detail & Related papers  (2025-11-27T11:43:50Z)
• LTD-Bench: Evaluating Large Language Models by Letting Them Draw [57.237152905238084]
  LTD-Bench is a breakthrough benchmark for large language models (LLMs)<n>It transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code.<n> LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity.
  arXiv  Detail & Related papers  (2025-11-04T08:11:23Z)
• Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward [1.7971686967440696]
  V$2$R-Bench is a benchmark framework for evaluating Visual Variation Robustness of LVLMs.<n>We show that advanced models that excel at complex vision-language tasks significantly underperform on simple tasks such as object recognition.<n>These vulnerabilities stem from error accumulation in the pipeline architecture and inadequate multimodal alignment.
  arXiv  Detail & Related papers  (2025-04-23T14:01:32Z)
• Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors [52.195637608631955]
  Non-line-of-sight (NLOS) imaging has attracted increasing attention due to its potential applications. Existing NLOS reconstruction approaches are constrained by the reliance on empirical physical priors. We introduce a novel learning-based solution, comprising two key designs: Learnable Path Compensation (LPC) and Adaptive Phasor Field (APF)
  arXiv  Detail & Related papers  (2024-09-21T04:39:45Z)
• Incorporating Degradation Estimation in Light Field Spatial Super-Resolution [54.603510192725786]
  We present LF-DEST, an effective blind Light Field SR method that incorporates explicit Degradation Estimation to handle various degradation types. We conduct extensive experiments on benchmark datasets, demonstrating that LF-DEST achieves superior performance across a variety of degradation scenarios in light field SR.
  arXiv  Detail & Related papers  (2024-05-11T13:14:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.