{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"id":"2106.12052","title":"Volume Rendering of Neural Implicit Surfaces","created":"2021-06-22","cited_by_count":996},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"id":"2103.15595","title":"MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo","created":"2021-03-29","cited_by_count":740},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"2101.10994","title":"Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes","created":"2021-01-26","cited_by_count":426},{"id":"1912.06378","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","created":"2019-12-13","cited_by_count":417},{"id":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"id":"2003.08981","title":"Local Implicit Grid Representations for 3D Scenes","created":"2020-03-19","cited_by_count":373},{"id":"1905.10711","title":"DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction","created":"2019-05-26","cited_by_count":333},{"id":"2003.10983","title":"Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction","created":"2020-03-24","cited_by_count":321},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"1902.10556","title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","created":"2019-02-27","cited_by_count":254},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"id":"2006.09662","title":"MetaSDF: Meta-learning Signed Distance Functions","created":"2020-06-17","cited_by_count":214},{"id":"2012.01411","title":"PatchmatchNet: Learned Multi-View Patchmatch Stereo","created":"2020-12-02","cited_by_count":207},{"id":"2003.10432","title":"Atlas: End-to-End 3D Scene Reconstruction from Posed Images","created":"2020-03-23","cited_by_count":206},{"id":"2202.06688","title":"Geometric Transformer for Fast and Robust Point Cloud Registration","created":"2022-02-14","cited_by_count":202},{"id":"1708.05375","title":"Learning a Multi-View Stereo Machine","created":"2017-08-17","cited_by_count":194},{"id":"2107.13421","title":"Neural Rays for Occlusion-aware Image-based Rendering","created":"2021-07-28","cited_by_count":192},{"id":"2109.01129","title":"NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo","created":"2021-09-02","cited_by_count":192},{"id":"1912.08329","title":"Cost Volume Pyramid Based Depth Inference for Multi-View Stereo","created":"2019-12-18","cited_by_count":154},{"id":"1911.12012","title":"Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness","created":"2019-11-27","cited_by_count":151},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"1908.04422","title":"Point-Based Multi-View Stereo Network","created":"2019-08-12","cited_by_count":147},{"id":"1708.01749","title":"SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis","created":"2017-08-05","cited_by_count":128},{"id":"2011.13650","title":"Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence","created":"2020-11-27","cited_by_count":119},{"id":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117},{"id":"1905.00538","title":"DPSNet: End-to-end Deep Plane Sweep Stereo","created":"2019-05-02","cited_by_count":115},{"id":"2003.13017","title":"Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement","created":"2020-03-29","cited_by_count":105},{"id":"2008.07928","title":"Visibility-aware Multi-view Stereo Network","created":"2020-08-18","cited_by_count":98},{"id":"1912.03203","title":"Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference","created":"2019-12-06","cited_by_count":91},{"id":"2011.14565","title":"Deep Implicit Templates for 3D Shape Representation","created":"2020-11-30","cited_by_count":86},{"id":"2007.10872","title":"Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking","created":"2020-07-21","cited_by_count":81},{"id":"2008.01639","title":"PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations","created":"2020-08-04","cited_by_count":81},{"id":"2108.09964","title":"Learning Signed Distance Field for Multi-view Surface Reconstruction","created":"2021-08-23","cited_by_count":76},{"id":"1812.03904","title":"Attention-guided Unified Network for Panoptic Segmentation","created":"2018-12-10","cited_by_count":71},{"id":"2108.03824","title":"AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network","created":"2021-08-09","cited_by_count":71},{"id":"2003.08593","title":"Curriculum DeepSDF","created":"2020-03-19","cited_by_count":62},{"id":"1912.11746","title":"Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume","created":"2019-12-26","cited_by_count":59},{"id":"1912.03001","title":"Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation","created":"2019-12-06","cited_by_count":44},{"id":"2104.13325","title":"MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions","created":"2021-04-27","cited_by_count":43},{"id":"2108.12966","title":"Digging into Uncertainty in Self-supervised Multi-view Stereo","created":"2021-08-30","cited_by_count":31},{"id":"1703.08836","title":"Learned Multi-Patch Similarity","created":"2017-03-26","cited_by_count":24},{"id":"2206.05375","title":"Generalizable Neural Radiance Fields for Novel View Synthesis with Transformer","created":"2022-06-10","cited_by_count":21},{"id":"2103.01530","title":"A Pose-only Solution to Visual Reconstruction and Navigation","created":"2021-03-02","cited_by_count":20},{"id":"2112.00336","title":"Multi-View Stereo with Transformer","created":"2021-12-01","cited_by_count":14},{"id":"2011.12722","title":"Attention Aware Cost Volume Pyramid Based Multi-view Stereo Network for 3D Reconstruction","created":"2020-11-25","cited_by_count":13},{"id":"1805.01556","title":"Pixel-wise Attentional Gating for Parsimonious Pixel Labeling","created":"2018-05-03","cited_by_count":12},{"id":"1808.06556","title":"Triangle Lasso for Simultaneous Clustering and Optimization in Graph Datasets","created":"2018-08-20","cited_by_count":8},{"id":"2204.01320","title":"RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo","created":"2022-04-04","cited_by_count":1}],"next_cursor":null}