32 citations · 35 across the 10 of their papers we have counts for
7 papers · 1 filter
Differentiable Polarized Path Tracing
Pramod Rao, Jérémy Riviere, Xilong Zhou +6
Physically based differentiable rendering has proven to be a powerful tool for inverse rendering problems (e.g., 3D reconstruction, reflectance estimation, lighting estimation). Ho…
OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control
Xilong Zhou, Jianchun Chen, Pramod Rao +7
We introduce OLATverse, a large-scale dataset comprising around 9M images of 765 real-world objects, captured from multiple viewpoints under a diverse set of precisely controlled l…
3DPR: Single Image 3D Portrait Relight using Generative Priors
Pramod Rao, Abhimitra Meka, Xilong Zhou +11
Rendering novel, relit views of a human head, given a monocular portrait image as input, is an inherently underconstrained problem. The traditional graphics solution is to explicit…
HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis
Timo Teufel, Pulkit Gera, Xilong Zhou +5
Simultaneous relighting and novel-view rendering of digital human representations is an important yet challenging task with numerous applications. Progress in this area has been si…
RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors
Avinash Paliwal, Xilong Zhou, Wei Ye +3
In this paper, we propose RI3D, a novel 3DGS-based approach that harnesses the power of diffusion models to reconstruct high-quality novel views given a sparse set of input images.…
PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion
Avinash Paliwal, Xilong Zhou, Andrii Tsarov +1
In this paper, we present PanoDreamer, a novel method for producing a coherent 360° 3D scene from a single input image. Unlike existing methods that generate the scene sequentially…
PhotoMat: A Material Generator Learned from Single Flash Photos
Xilong Zhou, Miloš Hašan, Valentin Deschaintre +4
Authoring high-quality digital materials is key to realism in 3D rendering. Previous generative models for materials have been trained exclusively on synthetic data; such data is l…