paper-with-me

Papers

3D Shape Completion with Test-Time Training

2024-10-24 · Michael Schopf-Kuester, Zorah Lähner, Michael Moeller

This work addresses the problem of \textit{shape completion}, i.e., the task of restoring incomplete shapes by predicting their missing parts. While previous works have often predicted the fractured and restored shape in one step, we approach the task by separately predicting the fractured and newly restored parts, but ensuring these predictions are interconnected. We use a decoder network motivated by related work on the prediction of signed distance functions (DeepSDF). In particular, our representation allows us to consider test-time-training, i.e., finetuning network parameters to match the given incomplete shape more accurately during inference. While previous works often have difficulties with artifacts around the fracture boundary, we demonstrate that our overfitting to the fractured parts leads to significant improvements in the restoration of eight different shape categories of the ShapeNet data set in terms of their chamfer distances.

📄 PDF Abstract BibTeX arXiv:2410.18668

Code (1)

mschopfkuester/shape_completion_ttt 공식 구현 pytorch

Tasks

Decoder

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Unsupervised Shape Completion via Deep Prior in the Neural Tangent Kernel Perspective

2021-04-19 · Lei Chu, Hao Pan, Wenping Wang

We present a novel approach for completing and reconstructing 3D shapes from incomplete scanned data by using deep neural networks. Rather than being trained on supervised completion tasks and applied on a testing shape,…

Shape Completion with Prediction of Uncertain Regions

2023-08-01 · Matthias Humt, Dominik Winkelbauer, Ulrich Hillenbrand

Shape completion, i.e., predicting the complete geometry of an object from a partial observation, is highly relevant for several downstream tasks, most notably robotic manipulation. When basing planning or prediction of …

ObjectPrediction

Self-supervised Shape Completion via Involution and Implicit Correspondences

2024-09-24 · Mengya Liu, Ajad Chhatkuli, Janis Postels, Luc van Gool 외

3D shape completion is traditionally solved using supervised training or by distribution learning on complete shape examples. Recently self-supervised learning approaches that do not require any complete 3D shape example…

Self-Supervised Learning

Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis

2016-12-01 · CVPR 2017 7 · Angela Dai, Charles Ruizhongtai Qi, Matthias Nießner

We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input shape, our method first infers a low-resol…

3D geometry3D Shape Generation

Diverse Plausible Shape Completions from Ambiguous Depth Images

2020-11-18 · Brad Saund, Dmitry Berenson

We propose PSSNet, a network architecture for generating diverse plausible 3D reconstructions from a single 2.5D depth image. Existing methods tend to produce only small variations on a single shape, even when multiple s…

DecoderDiversity