Related papers: Twinner: Shining Light on Digital Twins in a Few S…

Generating 3D scenes is a challenging open problem, which requires synthesizing plausible content that is fully consistent in 3D space. While recent methods such as neural radiance fields excel at view synthesis and 3D reconstruction, they…

Vision Transformer models trained on large-scale datasets, although effective, often exhibit artifacts in the patch token they extract. While such defects can be alleviated by re-training the entire model with additional classification…

Achieving high-fidelity 3D surface reconstruction while preserving fine details remains challenging, especially in the presence of materials with complex reflectance properties and without a dense-view setup. In this paper, we introduce a…

Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion. Recent NeRF based methods achieve impressive fidelity of 3D reconstruction, but bake…

Generating 3D models from multi-view 2D RGB images has gained significant attention, extending the capabilities of technologies like Virtual Reality, Robotic Vision, and human-machine interaction. In this paper, we introduce a hybrid…

We present a complete system for real-time rendering of scenes with complex appearance previously reserved for offline use. This is achieved with a combination of algorithmic and system level innovations. Our appearance model utilizes…

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…

We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered,…

Event cameras are rapidly emerging as powerful vision sensors for 3D reconstruction, uniquely capable of asynchronously capturing per-pixel brightness changes. Compared to traditional frame-based cameras, event cameras produce sparse yet…

Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…

We propose a new technique for estimating spatially varying parametric materials from a single image of an object with unknown shape in unknown illumination. Our method uses a low-order parametric reflectance model, and incorporates strong…

We present InvRGB+L, a novel inverse rendering model that reconstructs large, relightable, and dynamic scenes from a single RGB+LiDAR sequence. Conventional inverse graphics methods rely primarily on RGB observations and use LiDAR mainly…

The development of large-scale 3D scene reconstruction and novel view synthesis methods mostly rely on datasets comprising perspective images with narrow fields of view (FoV). While effective for small-scale scenes, these datasets require…

Image captured under low-light conditions presents unpleasing artifacts, which debilitate the performance of feature extraction for many upstream visual tasks. Low-light image enhancement aims at improving brightness and contrast, and…

Mirror reflections are common in everyday environments and can provide stereo information within a single capture, as the real and reflected virtual views are visible simultaneously. We exploit this property by treating the reflection as an…

Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often…

We present RenderFormer, a neural rendering pipeline that directly renders an image from a triangle-based representation of a scene with full global illumination effects and that does not require per-scene training or fine-tuning. Instead…

Implicit neural representation has opened up new possibilities for inverse rendering. However, existing implicit neural inverse rendering methods struggle to handle strongly illuminated scenes with significant shadows and indirect…

Image relighting has emerged as a problem of significant research interest inspired by augmented reality applications. Physics-based traditional methods, as well as black box deep learning models, have been developed. The existing deep…

We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks. Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances…