arXiv subjects

Julie Dorsey

Publications and source records attributed to Julie Dorsey.

9 recordsLinked to original sources

arXiv2026

TokenLight: Precise Lighting Control in Images using Attribute Tokens

This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a conditional image generation task and introduce attribute tokens to encode distinct lighting factors such as intensity, color, ambient illumination, diffuse level, and 3D light positions. The model is trained on a large-scale synthetic dataset with ground-truth lighting annotations, supplemented by a small set of real captures to enhance realism and generalization. We validate our approach across a variety of relighting tasks, including controlling in-scene lighting fixtures and editing environment illumination using virtual light sources, on synthetic and real images. Our method achieves state-of-the-art quantitative and qualitative performance compared to prior work. Remarkably, without explicit inverse rendering supervision, the model exhibits an inherent understanding of how light interacts with scene geometry, occlusion, and materials, yielding convincing lighting effects even in traditionally challenging scenarios such as placing lights within objects or relighting transparent materials plausibly. Project page: vrroom.github.io/tokenlight/

cs.CV↗

arXiv2025

Generating 360° Video is What You Need For a 3D Scene

Generating 3D scenes is still a challenging task due to the lack of readily available scene data. Most existing methods only produce partial scenes and provide limited navigational freedom. We introduce a practical and scalable solution that uses 360° video as an intermediate scene representation, capturing the full-scene context and ensuring consistent visual content throughout the generation. We propose WorldPrompter, a generative pipeline that synthesizes traversable 3D scenes from text prompts. WorldPrompter incorporates a conditional 360° panoramic video generator, capable of producing a 128-frame video that simulates a person walking through and capturing a virtual environment. The resulting video is then reconstructed as Gaussian splats by a fast feedforward 3D reconstructor, enabling a true walkable experience within the 3D scene. Experiments demonstrate that our panoramic video generation model, trained with a mix of image and video data, achieves convincing spatial and temporal consistency for static scenes. This is validated by an average COLMAP matching rate of 94.6\%, allowing for high-quality panoramic Gaussian splat reconstruction and improved navigation throughout the scene. Qualitative and quantitative results also show it outperforms the state-of-the-art 360° video generators and 3D scene generation models.

cs.GR↗

arXiv2025

Digital Salon: An AI and Physics-Driven Tool for 3D Hair Grooming and Simulation

We introduce Digital Salon, a comprehensive hair authoring system that supports real-time 3D hair generation, simulation, and rendering. Unlike existing methods that focus on isolated parts of 3D hair modeling and involve a heavy computation process or network training, Digital Salon offers a holistic and interactive system that lowers the technical barriers of 3D hair modeling through natural language-based interaction. The system guides users through four key stages: text-guided hair retrieval, real-time hair simulation, interactive hair refinement, and hair-conditioned image generation. This cohesive workflow makes advanced hair design accessible to users of varying skill levels and dramatically streamlines the creative process in digital media with an intuitive, versatile, and efficient solution for hair modeling. User studies show that our system can outperform traditional hair modeling workflows for rapid prototyping. Furthermore, we provide insights into the benefits of our system with future potential of deploying our system in real salon environments. More details can be found on our project page: https://digital-salon.github.io/.

cs.GR↗

arXiv2025

SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces

We introduce SynthLight, a diffusion model for portrait relighting. Our approach frames image relighting as a re-rendering problem, where pixels are transformed in response to changes in environmental lighting conditions. Using a physically-based rendering engine, we synthesize a dataset to simulate this lighting-conditioned transformation with 3D head assets under varying lighting. We propose two training and inference strategies to bridge the gap between the synthetic and real image domains: (1) multi-task training that takes advantage of real human portraits without lighting labels; (2) an inference time diffusion sampling procedure based on classifier-free guidance that leverages the input portrait to better preserve details. Our method generalizes to diverse real photographs and produces realistic illumination effects, including specular highlights and cast shadows, while preserving the subject's identity. Our quantitative experiments on Light Stage data demonstrate results comparable to state-of-the-art relighting methods. Our qualitative results on in-the-wild images showcase rich and unprecedented illumination effects. Project Page: \url{https://vrroom.github.io/synthlight/}

cs.CV↗

arXiv2024

All-day Depth Completion

We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take as input an additional synchronized sparse point cloud (i.e., from a LiDAR) projected onto the image plane as a sparse depth map, along with a camera image. The crux of our method lies in the use of the abundantly available synthetic data to first approximate the 3D scene structure by learning a mapping from sparse to (coarse) dense depth maps along with their predictive uncertainty - we term this, SpaDe. In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme. The resulting depth completion network leverages complementary strengths from both modalities - depth is sparse but insensitive to illumination and in metric scale, and image is dense but sensitive with scale ambiguity. SpaDe can be used in a plug-and-play fashion, which allows for 25% improvement when augmented onto existing methods to preprocess sparse depth. We demonstrate URL on the nuScenes dataset where we improve over all baselines by an average 11.65% in all-day scenarios, 11.23% when tested specifically for daytime, and 13.12% for nighttime scenes.

cs.CV↗

arXiv2022

Countering Racial Bias in Computer Graphics Research

Current computer graphics research practices contain racial biases that have resulted in investigations into "skin" and "hair" that focus on the hegemonic visual features of Europeans and East Asians. To broaden our research horizons to encompass all of humanity, we propose a variety of improvements to quantitative measures and qualitative practices, and pose novel, open research problems.

cs.GR↗

arXiv2021

An Inverse Procedural Modeling Pipeline for SVBRDF Maps

Procedural modeling is now the de facto standard of material modeling in industry. Procedural models can be edited and are easily extended, unlike pixel-based representations of captured materials. In this paper, we present a semi-automatic pipeline for general material proceduralization. Given Spatially-Varying Bidirectional Reflectance Distribution Functions (SVBRDFs) represented as sets of pixel maps, our pipeline decomposes them into a tree of sub-materials whose spatial distributions are encoded by their associated mask maps. This semi-automatic decomposition of material maps progresses hierarchically, driven by our new spectrum-aware material matting and instance-based decomposition methods. Each decomposed sub-material is proceduralized by a novel multi-layer noise model to capture local variations at different scales. Spatial distributions of these sub-materials are modeled either by a by-example inverse synthesis method recovering Point Process Texture Basis Functions (PPTBF) or via random sampling. To reconstruct procedural material maps, we propose a differentiable rendering-based optimization that recomposes all generated procedures together to maximize the similarity between our procedural models and the input material pixel maps. We evaluate our pipeline on a variety of synthetic and real materials. We demonstrate our method's capacity to process a wide range of material types, eliminating the need for artist designed material graphs required in previous work. As fully procedural models, our results expand to arbitrary resolution and enable high level user control of appearance.

cs.GR↗

arXiv2018

AniCode: Authoring Coded Artifacts for Network-Free Personalized Animations

Time-based media (videos, synthetic animations, and virtual reality experiences) are used for communication, in applications such as manufacturers explaining the operation of a new appliance to consumers and scientists illustrating the basis of a new conclusion. However, authoring time-based media that are effective and personalized for the viewer remains a challenge. We introduce AniCode, a novel framework for authoring and consuming time-based media. An author encodes a video animation in a printed code, and affixes the code to an object. A consumer uses a mobile application to capture an image of the object and code, and to generate a video presentation on the fly. Importantly, AniCode presents the video personalized in the consumer's visual context. Our system is designed to be low cost and easy to use. By not requiring an internet connection, and through animations that decode correctly only in the intended context, AniCode enhances privacy of communication using time-based media. Animation schemes in the system include a series of 2D and 3D geometric transformations, color transformation, and annotation. We demonstrate the AniCode framework with sample applications from a wide range of domains, including product "how to" examples, cultural heritage, education, creative art, and design. We evaluate the ease of use and effectiveness of our system with a user study.

cs.GR↗

arXiv2014

Ergonomic-driven Geometric Exploration and Reshaping

The paper addresses the following problem: given a set of man-made shapes, e.g., chairs, can we quickly rank and explore the set of shapes with respect to a given avatar pose? Answering this question requires identifying which shapes are more suitable for the defined avatar and pose; and moreover, to provide fast preview of how to alter the input geometry to better fit the deformed shapes to the given avatar pose? The problem naturally links physical proportions of human body and its interaction with object shapes in an attempt to connect ergonomics with shape geometry. We designed an interaction system that allows users to explore shape collections using the deformation of human characters while at the same time providing interactive previews of how to alter the shapes to better fit the user-specified character. We achieve this by first mapping ergonomics guidelines into a set of simultaneous multi-part constraints based on target contacts; and then, proposing a novel contact-based deformation model to realize multi-contact constraints. We evaluate our framework on various chair models and validate the results via a small user study.

cs.GR↗