paper-with-me

홈 › Papers

ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction

2022-12-08 · CVPR 2023 1 · Zhen Wang, Shijie Zhou, Jeong Joon Park, Despoina Paschalidou, Suya You, Gordon Wetzstein, Leonidas Guibas, Achuta Kadambi

This work introduces alternating latent topologies (ALTO) for high-fidelity reconstruction of implicit 3D surfaces from noisy point clouds. Previous work identifies that the spatial arrangement of latent encodings is important to recover detail. One school of thought is to encode a latent vector for each point (point latents). Another school of thought is to project point latents into a grid (grid latents) which could be a voxel grid or triplane grid. Each school of thought has tradeoffs. Grid latents are coarse and lose high-frequency detail. In contrast, point latents preserve detail. However, point latents are more difficult to decode into a surface, and quality and runtime suffer. In this paper, we propose ALTO to sequentially alternate between geometric representations, before converging to an easy-to-decode latent. We find that this preserves spatial expressiveness and makes decoding lightweight. We validate ALTO on implicit 3D recovery and observe not only a performance improvement over the state-of-the-art, but a runtime improvement of 3-10$\times$. Project website at https://visual.ee.ucla.edu/alto.htm/.

📄 PDF Abstract BibTeX arXiv:2212.04096

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionLicense Plate Recognition

Similar Papers 제목 키워드 기반

DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction

2024-03-08 · CVPR 2024 1 · Jaehyeok Shim, Kyungdon Joo

We propose a novel concept of dual and integrated latent topologies (DITTO in short) for implicit 3D reconstruction from noisy and sparse point clouds. Most existing methods predominantly focus on single latent type, suc…

3D ReconstructionDecoder

Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes

2022-06-10 · CVPR 2022 1 · Ka-Hei Hui, Ruihui Li, Jingyu Hu, Chi-Wing Fu

This paper introduces a novel framework called DTNet for 3D mesh reconstruction and generation via Disentangled Topology. Beyond previous works, we learn a topology-aware neural template specific to each input then defor…

Hyperrealistic neural decoding: Reconstruction of face stimuli from fMRI measurements via the GAN latent space

2021-01-01 · Thirza Dado, Yağmur Güçlütürk, Luca Ambrogioni, Gabrielle Ras 외

We introduce a new framework for hyperrealistic reconstruction of perceived naturalistic stimuli from brain recordings. To this end, we embrace the use of generative adversarial networks (GANs) at the earliest step of ou…

On the Effectiveness of Weight-Encoded Neural Implicit 3D Shapes

2020-09-17 · Thomas Davies, Derek Nowrouzezahrai, Alec Jacobson

A neural implicit outputs a number indicating whether the given query point in space is inside, outside, or on a surface. Many prior works have focused on _latent-encoded_ neural implicits, where a latent vector encoding…

3D Shape Representation

Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization

2024-11-20 · Sanghyeob Song, Jaihyun Lew, Hyemi Jang, Sungroh Yoon

Estimating the homography between two images is crucial for mid- or high-level vision tasks, such as image stitching and fusion. However, using supervised learning methods is often challenging or costly due to the diffic…

Homography EstimationImage Stitching