paper-with-me

홈 › Papers

Neural 3D Mesh Renderer

2017-11-20 · CVPR 2018 6 · Hiroharu Kato, Yoshitaka Ushiku, Tatsuya Harada

For modeling the 3D world behind 2D images, which 3D representation is most appropriate? A polygon mesh is a promising candidate for its compactness and geometric properties. However, it is not straightforward to model a polygon mesh from 2D images using neural networks because the conversion from a mesh to an image, or rendering, involves a discrete operation called rasterization, which prevents back-propagation. Therefore, in this work, we propose an approximate gradient for rasterization that enables the integration of rendering into neural networks. Using this renderer, we perform single-image 3D mesh reconstruction with silhouette image supervision and our system outperforms the existing voxel-based approach. Additionally, we perform gradient-based 3D mesh editing operations, such as 2D-to-3D style transfer and 3D DeepDream, with 2D supervision for the first time. These applications demonstrate the potential of the integration of a mesh renderer into neural networks and the effectiveness of our proposed renderer.

📄 PDF Abstract BibTeX arXiv:1711.07566

Code (3)

laughtervv/tf_neural_renderer tf
mattiagaggi/3D-Pose-Estimator---MSc_project pytorch
monniert/unicorn pytorch

Tasks

3D Object ReconstructionStyle Transfer

Similar Papers 제목 키워드 기반

Gaussian Mesh Renderer for Lightweight Differentiable Rendering

2026-02-16 · Xinpeng Liu, Fumio Okura arxiv

3D Gaussian Splatting (3DGS) has enabled high-fidelity virtualization with fast rendering and optimization for novel view synthesis. On the other hand, triangle mesh models still remain a popular choice for surface recon…

Novel View Synthesis

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings

2021-04-27 · CVPR 2022 1 · Innfarn Yoo, Huiwen Chang, Xiyang Luo, Ondrej Stava 외

Digital watermarking is widely used for copyright protection. Traditional 3D watermarking approaches or commercial software are typically designed to embed messages into 3D meshes, and later retrieve the messages directl…

Decoder

Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning

2019-04-03 · ICCV 2019 10 · Shichen Liu, Tianye Li, Weikai Chen, Hao Li

Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation. By inverting such renderer, one can think of a learning approach to infer 3D information from 2D images. Ho…

3D Object ReconstructionSingle-View 3D Reconstruction

Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization

2026-06-26 · David Charatan, Daniel Xu, Richard Szeliski, George Kopanas 외 arxiv

Differentiable rendering has emerged as a powerful approach for 3D reconstruction and novel view synthesis. State-of-the-art differentiable rendering methods combine a variety of custom representations of 3D geometry and…

Novel View Synthesis3D Reconstruction

MeshAdv: Adversarial Meshes for Visual Recognition

2018-10-11 · CVPR 2019 6 · Chaowei Xiao, Dawei Yang, Bo Li, Jia Deng 외

Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted in…