Related papers: Generating Parametric BRDFs from Natural Language …

Recent neural rendering methods have demonstrated accurate view interpolation by predicting volumetric density and color with a neural network. Although such volumetric representations can be supervised on static and dynamic scenes,…

Large vision-language models are steadily gaining personalization capabilities at the cost of fine-tuning or data augmentation. We present two models for image generation using model-agnostic learning that align semantic priors with…

We formulate SVBRDF estimation from photographs as a diffusion task. To model the distribution of spatially varying materials, we first train a novel unconditional SVBRDF diffusion backbone model on a large set of 312,165 synthetic…

We propose NEMTO, the first end-to-end neural rendering pipeline to model 3D transparent objects with complex geometry and unknown indices of refraction. Commonly used appearance modeling such as the Disney BSDF model cannot accurately…

We present multispectral rendering techniques for visualizing layered materials found in biological specimens. We are the first to use acquired data from the near-infrared and ultraviolet spectra for non-photorealistic rendering (NPR).…

This research paper proposes a Latent Diffusion Model for 3D (LDM3D) that generates both image and depth map data from a given text prompt, allowing users to generate RGBD images from text prompts. The LDM3D model is fine-tuned on a dataset…

Existing large language models (LLMs) are known for generating "hallucinated" content, namely a fabricated text of plausibly looking, yet unfounded, facts. To identify when these hallucination scenarios occur, we examine the properties of…

Humans describe the physical world using natural language to refer to specific 3D locations based on a vast range of properties: visual appearance, semantics, abstract associations, or actionable affordances. In this work we propose…

A method to obtain three-dimensional data of real-world objects by integrating their material properties is presented. The material properties are defined by capturing the Reflectance Fields of the real-world objects. It is shown, unlike…

We present Material Anything, a fully-automated, unified diffusion framework designed to generate physically-based materials for 3D objects. Unlike existing methods that rely on complex pipelines or case-specific optimizations, Material…

We present a method for generating physically-based materials for 3D shapes based on a video diffusion transformer architecture. Our method is conditioned on input geometry and a text description, and jointly models multiple material…

We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. Previous work on learning shape reconstruction from multiple views uses discrete…

Manual modeling of material parameters and 3D geometry is a time consuming yet essential task in the gaming and film industries. While recent advances in 3D reconstruction have enabled accurate approximations of scene geometry and…

Light-matter interactions within indoor environments are significantly depolarizing. Nonetheless, the relatively small polarization attributes are informative. To make use of this information, polarized-BRDF (pBRDF) models for common indoor…

Recently, the surge of efficient and automated 3D AI-generated content (AIGC) methods has increasingly illuminated the path of transforming human imagination into complex 3D structures. However, the automated generation of 3D content is…

Editing a local region or a specific object in a 3D scene represented by a NeRF or consistently blending a new realistic object into the scene is challenging, mainly due to the implicit nature of the scene representation. We present…

We address the problem of recovering the shape and spatially-varying reflectance of an object from multi-view images (and their camera poses) of an object illuminated by one unknown lighting condition. This enables the rendering of novel…

In this paper, we propose a novel end-to-end relightable neural inverse rendering system that achieves high-quality reconstruction of geometry and material properties, thus enabling high-quality relighting. The cornerstone of our method is…

We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material explanations represented as albedo, roughness, and metallic maps.…

Text-driven localized editing of 3D objects is particularly difficult as locally mixing the original 3D object with the intended new object and style effects without distorting the object's form is not a straightforward process. To address…