Related papers: OpenRR-1k: A Scalable Dataset for Real-World Refle…
Score-based diffusion models learn to reverse a stochastic differential equation that maps data to noise. However, for complex tasks, numerical error can compound and result in highly unnatural samples. Previous work mitigates this drift…
Recent advancements in 3D Gaussian Splatting (3D-GS) have revolutionized novel view synthesis, facilitating real-time, high-quality image rendering. However, in scenarios involving reflective surfaces, particularly mirrors, 3D-GS often…
Neural Radiance Fields (NeRF) has achieved unprecedented view synthesis quality using coordinate-based neural scene representations. However, NeRF's view dependency can only handle simple reflections like highlights but cannot deal with…
Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently…
As robotic technology rapidly develops, robots are being employed in an increasing number of fields. However, due to the complexity of deployment environments or the prevalence of ambiguous-condition objects, the practical application of…
Data-driven developments in lensless imaging, such as machine learning-based reconstruction algorithms, require large datasets. In this work, we introduce a data acquisition pipeline that can capture from multiple lensless imaging systems…
Image composition involves inserting a foreground object into the background while synthesizing environment-consistent effects such as shadows and reflections. Although shadow generation has been extensively studied, reflection generation…
Recent advances in deep learning, such as neural radiance fields and implicit neural representations, have significantly advanced 3D reconstruction. However, accurately reconstructing objects with complex optical properties, such as metals,…
Anomaly detection is a core capability for robotic perception and industrial inspection, yet most existing benchmarks are collected under controlled conditions with fixed viewpoints and stable illumination, failing to reflect real…
We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object from a sparse set of only six images captured by wide-baseline cameras under collocated point…
Learning-based image deraining methods have made great progress. However, the lack of large-scale high-quality paired training samples is the main bottleneck to hamper the real image deraining (RID). To address this dilemma and advance RID,…
Recent single-image relighting methods, powered by advanced generative models, have achieved impressive photorealism on synthetic benchmarks. However, their effectiveness in the complex visual landscape of the real world remains largely…
We introduce a novel method for using reflectance to identify materials. Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionality. In this work,…
Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded within model weights. However, existing LRMs often suffer from…
This paper presents a method to detect reflection of 3D light detection and ranging (Lidar) scans and uses it to classify the points and also map objects outside the line of sight. Our software uses several approaches to analyze the point…
Modern cameras with large apertures often suffer from a shallow depth of field, resulting in blurry images of objects outside the focal plane. This limitation is particularly problematic for fixed-focus cameras, such as those used in smart…
Deepfakes, synthetic media created using advanced AI techniques, pose a growing threat to information integrity, particularly in politically sensitive contexts. This challenge is amplified by the increasing realism of modern generative…
We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the…
Existing image super-resolution (SR) techniques often fail to generalize effectively in complex real-world settings due to the significant divergence between training data and practical scenarios. To address this challenge, previous efforts…
Since its release, ImageNet-1k dataset has become a gold standard for evaluating model performance. It has served as the foundation for numerous other datasets and training tasks in computer vision. As models have improved in accuracy,…