paper-with-me

Papers

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

2019-05-26 · NeurIPS 2019 12 · Qiangeng Xu, Weiyue Wang, Duygu Ceylan, Radomir Mech, Ulrich Neumann

Reconstructing 3D shapes from single-view images has been a long-standing research problem. In this paper, we present DISN, a Deep Implicit Surface Network which can generate a high-quality detail-rich 3D mesh from an 2D image by predicting the underlying signed distance fields. In addition to utilizing global image features, DISN predicts the projected location for each 3D point on the 2D image, and extracts local features from the image feature maps. Combining global and local features significantly improves the accuracy of the signed distance field prediction, especially for the detail-rich areas. To the best of our knowledge, DISN is the first method that constantly captures details such as holes and thin structures present in 3D shapes from single-view images. DISN achieves the state-of-the-art single-view reconstruction performance on a variety of shape categories reconstructed from both synthetic and real images. Code is available at https://github.com/xharlie/DISN The supplementary can be found at https://xharlie.github.io/images/neurips_2019_supp.pdf

📄 PDF Abstract BibTeX arXiv:1905.10711

Code (3)

Xharlie/DISN 공식 구현 tf
Xharlie/ShapenetRender_more_variation 공식 구현
laughtervv/DISN 공식 구현 tf

Tasks

3D ReconstructionSingle-View 3D Reconstruction

Similar Papers 제목 키워드 기반

SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images

2020-08-13 · Jiapeng Tang, Xiaoguang Han, Mingkui Tan, Xin Tong 외

This paper focuses on the challenging task of learning 3D object surface reconstructions from RGB images. Existingmethods achieve varying degrees of success by using different surface representations. However, they all h…

Surface Reconstruction

NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects

2023-03-21 · ICCV 2023 1 · Dongqing Wang, Tong Zhang, Sabine Süsstrunk

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 ca…

Image MattingNeural RenderingObjectTransparent objects

AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist?

2026-02-24 · Hailong Yan, Shice Liu, Tao Wang, Xiangtao Zhang 외 arxiv

Custom Storyboard Generation (CSG) aims to produce high-quality, multi-character consistent storytelling. Current approaches based on static diffusion models, whether used in a one-shot manner or within multi-agent frame…

KU_ED at SocialDisNER: Extracting Disease Mentions in Tweets Written in Spanish

2022-10-01 · SMM4H (COLING) 2022 10 · Antoine Lain, Wonjin Yoon, Hyunjae Kim, Jaewoo Kang 외

This paper describes our system developed for the Social Media Mining for Health (SMM4H) 2022 SocialDisNER task. We used several types of pre-trained language models, which are trained on Spanish biomedical literature or…

Disentangled Noisy Correspondence Learning

2024-08-10 · Zhuohang Dang, Minnan Luo, Jihong Wang, Chengyou Jia 외

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably invol…

cross-modal alignmentCross-Modal RetrievalDisentanglementMutual Information Estimation