Referenced Papers (7)
Illustrious: An open advanced illustration model
Sang Hyun Park, Jun Young Koh, Junha Lee, Joy Song, Dongha Kim, Hoyeon Moon
arXiv [cs.CV], 2024
"This paper is shown as an example of a previous technique that produces low-resolution or coarse 3D simulations from input data."
CAST: Component-Aligned 3D Scene Reconstruction from an RGB image
Kaixin Yao, Longwen Zhang, Xinhao Yan, Yan Zeng, Qixuan Zhang, Wei Yang
arXiv [cs.CV], 2025
"This paper presents a novel method for 3D scene reconstruction from a single RGB image, overcoming previous challenges in object alignment and physical realism within complex scenes."
Difix3D+: Improving 3D reconstructions with single-step diffusion models
Jay Zhangjie Wu, Yuxuan Zhang, Haithem Turki, Xuanchi Ren, Jun Gao, Mike Zheng Shou
ArXiv, 2025
"This paper introduces a breakthrough diffusion-based technique for improving 3D reconstructions by enhancing noisy initial outputs, significantly reducing visual artifacts and improving overall quality for virtual world rendering."
DreamFusion: Text-to-3D using 2D Diffusion
Ben Poole, Ajay Jain, Jonathan T Barron, Ben Mildenhall
arXiv [cs.CV], 2022
"This paper is cited as an example of older techniques for generating 3D objects from text, highlighting their coarse and unrealistic output."
Neural Crossbreed: Neural based image metamorphosis
Sanghun Park, Kwanggyoon Seo, Junyong Noh
arXiv [cs.CV], 2020
"This paper demonstrates methods for novel view synthesis and depth estimation from visual input, representing foundational work in recreating realistic scenes."
NeRF: Representing scenes as neural radiance fields for view synthesis
Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, Ren Ng
arXiv [cs.CV], 2020
"This paper introduces the seminal NERF (Neural Radiance Fields) technique, which learns 3D scene representations from 2D images, allowing for rendering from novel viewpoints."
3D Gaussian splatting for real-time radiance Field rendering
Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George Drettakis
arXiv [cs.GR], 2023
"This paper introduces anisotropic volumetric 3D Gaussians for capturing detailed facial motions and rendering them at high resolutions, marking a significant step towards realistic human avatar generation."