arXiv subjects

Kebin Contreras

Publications and source records attributed to Kebin Contreras.

6 recordsLinked to original sources

arXiv2026

Time-Reversed Imaging: A Multimodal Benchmark and Framework for Reconstructing Past Human-Environment Interactions

We introduce time-reversed imaging, a new paradigm that infers what just happened in a scene from fading multimodal traces. Instead of extrapolating or interpolating video frames, our goal is to infer past human-environment interactions from residual physical imprints observable in thermal, ultraviolet, and visible spectra. To study this problem, we present TRACE-HEI, the first proof-of-concept dataset for time-reversed imaging, containing synchronized tri-modal video sequences of actions such as sitting, touching, moving objects, and liquid spills, captured across diverse materials and recorded up to three minutes after contact. To establish the benchmark, we propose a multimodal inference approach that extracts structured textual descriptions of detected traces and uses them to constrain a vision-language-guided diffusion model for reconstructing plausible past frames. Experiments show that inferring recent events from fading traces is challenging but feasible when complementary modalities reduce solution ambiguity. This work defines the first computational and experimental foundation for time-reversed imaging, bridging vision, physics, and generative reasoning, and opening new directions for scene understanding beyond instantaneous observation.

cs.CV↗

arXiv2026

ProjGuard: Safety Monitoring for Computer-Use Agents via Low-Dimensional Projections

Computer-use agents are increasingly capable of operating on real operating systems, but this capability has also increased the risks posed by prompt injection, indirect instructions, and visual attacks. Existing defenses typically rely on analyzing the prompt or each potentially malicious input with a second large model at inference time, which can limit coverage or increase deployment cost. We propose ProjGuard, an alternative based on behavioral trajectory monitoring. At each step, we derive a lightweight scalar risk signal from the agent's accumulated interaction history and evaluate, online, whether execution is beginning to drift toward an unsafe region. This enables early warnings before the trajectory reaches a potentially harmful action. When an alert is raised, we selectively activate an auxiliary vision-language model to propose a corrected next step and steer execution back toward task completion. Experiments on OS-Harm show that monitoring with on-demand correction reduces the unsafe rate from 16 percent to 3 percent while improving task completion from 59 percent to 65 percent. We further evaluate transfer to RiosWorld, where the method remains competitive, reaching 4 percent unsafe and 64 percent completion. Overall, these results support a hierarchical safety strategy in which always-on monitoring anticipates deviations and activates correction only when needed.

stat.CO↗

arXiv2025

Learning-based Spectral Regression for Cocoa Bean Physicochemical Property Prediction

Cocoa bean quality assessment is essential for ensuring compliance with commercial standards, protecting consumer health, and increasing the market value of the cocoa product. The quality assessment estimates key physicochemical properties, such as fermentation level, moisture content, polyphenol concentration, and cadmium content, among others. This assessment has traditionally relied on the accurate estimation of these properties via visual or sensory evaluation, jointly with laboratory-based physicochemical analyses, which are often time-consuming, destructive, and difficult to scale. This creates the need for rapid, reliable, and noninvasive alternatives. Spectroscopy, particularly in the visible and near-infrared ranges, offers a non-invasive alternative by capturing the molecular signatures associated with these properties. Therefore, this work introduces a scalable methodology for evaluating the quality of cocoa beans by predicting key physicochemical properties from the spectral signatures of cocoa beans. This approach utilizes a conveyor belt system integrated with a VIS-NIR spectrometer, coupled with learning-based regression models. Furthermore, a dataset is built using cocoa bean batches from Santander, Colombia. Ground-truth reference values were obtained through standardized laboratory analyses and following commercial cocoa quality regulations. To further evaluate the proposed methodology's generalization, performance is tested on samples collected from other Colombian regions and from Cusco, Peru. Experimental results show that the proposed models achieved R2 scores exceeding 0.98 across all physicochemical properties, and reached 0.96 accuracy on geographically independent samples. This non-destructive approach represents a suitable and scalable alternative to conventional laboratory methods for quality assessment across the cocoa production chain.

eess.SP↗

arXiv2025

See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Models

Recovering the past from present observations is an intriguing challenge with potential applications in forensics and scene analysis. Thermal imaging, operating in the infrared range, provides access to otherwise invisible information. Since humans are typically warmer (37 C -98.6 F) than their surroundings, interactions such as sitting, touching, or leaning leave residual heat traces. These fading imprints serve as passive temporal codes, allowing for the inference of recent events that exceed the capabilities of RGB cameras. This work proposes a time-reversed reconstruction framework that uses paired RGB and thermal images to recover scene states from a few seconds earlier. The proposed approach couples Visual-Language Models (VLMs) with a constrained diffusion process, where one VLM generates scene descriptions and another guides image reconstruction, ensuring semantic and structural consistency. The method is evaluated in three controlled scenarios, demonstrating the feasibility of reconstructing plausible past frames up to 120 seconds earlier, providing a first step toward time-reversed imaging from thermal traces.

cs.CV↗

arXiv2025

High Dynamic Range Modulo Imaging for Robust Object Detection in Autonomous Driving

Object detection precision is crucial for ensuring the safety and efficacy of autonomous driving systems. The quality of acquired images directly influences the ability of autonomous driving systems to correctly recognize and respond to other vehicles, pedestrians, and obstacles in real-time. However, real environments present extreme variations in lighting, causing saturation problems and resulting in the loss of crucial details for detection. Traditionally, High Dynamic Range (HDR) images have been preferred for their ability to capture a broad spectrum of light intensities, but the need for multiple captures to construct HDR images is inefficient for real-time applications in autonomous vehicles. To address these issues, this work introduces the use of modulo sensors for robust object detection. The modulo sensor allows pixels to `reset/wrap' upon reaching saturation level by acquiring an irradiance encoding image which can then be recovered using unwrapping algorithms. The applied reconstruction techniques enable HDR recovery of color intensity and image details, ensuring better visual quality even under extreme lighting conditions at the cost of extra time. Experiments with the YOLOv10 model demonstrate that images processed using modulo images achieve performance comparable to HDR images and significantly surpass saturated images in terms of object detection accuracy. Moreover, the proposed modulo imaging step combined with HDR image reconstruction is shorter than the time required for conventional HDR image acquisition.

cs.CV↗

arXiv2025

Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications

High dynamic range (HDR) imaging is vital for capturing the full range of light tones in scenes, essential for computer vision tasks such as autonomous driving. Standard commercial imaging systems face limitations in capacity for well depth, and quantization precision, hindering their HDR capabilities. Modulo imaging, based on unlimited sampling (US) theory, addresses these limitations by using a modulo analog-to-digital approach that resets signals upon saturation, enabling estimation of pixel resets through neighboring pixel intensities. Despite the effectiveness of (US) algorithms in one-dimensional signals, their optimization problem for two-dimensional signals remains unclear. This work formulates the US framework as an autoregressive $\ell_2$ phase unwrapping problem, providing computationally efficient solutions in the discrete cosine domain jointly with a stride removal algorithm also based on spatial differences. By leveraging higher-order finite differences for two-dimensional images, our approach enhances HDR image reconstruction from modulo images, demonstrating its efficacy in improving object detection in autonomous driving scenes without retraining.

eess.IV↗