{"list":"other","total":110,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2302.00482","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","created":"2023-02-01","cited_by_count":879},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"2102.05379","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","created":"2021-02-10","cited_by_count":574},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2111.08005","title":"Solving Inverse Problems in Medical Imaging with Score-Based Generative Models","created":"2021-11-15","cited_by_count":521},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2301.11093","title":"Simple diffusion: End-to-end diffusion for high resolution images","created":"2023-01-26","cited_by_count":422},{"id":"1606.05830","title":"Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age","created":"2016-06-19","cited_by_count":411},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"2412.06264","title":"Flow Matching Guide and Code","created":"2024-12-09","cited_by_count":301},{"id":"1806.05034","title":"A Probabilistic U-Net for Segmentation of Ambiguous Images","created":"2018-06-13","cited_by_count":283},{"id":"2311.07885","title":"One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion","created":"2023-11-14","cited_by_count":283},{"id":"2304.02602","title":"Generative Novel View Synthesis with 3D-Aware Diffusion Models","created":"2023-04-05","cited_by_count":274},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188},{"id":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"id":"2308.01557","title":"Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models","created":"2023-08-03","cited_by_count":161},{"id":"1611.03631","title":"Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning","created":"2016-11-11","cited_by_count":150},{"id":"1712.09763","title":"PixelSNAIL: An Improved Autoregressive Generative Model","created":"2017-12-28","cited_by_count":137},{"id":"2505.12549","title":"VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold","created":"2025-05-18","cited_by_count":136},{"id":"2306.11719","title":"Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision","created":"2023-06-20","cited_by_count":112},{"id":"2310.17994","title":"ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image","created":"2023-10-27","cited_by_count":111},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"1901.03861","title":"HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation","created":"2019-01-12","cited_by_count":108},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96},{"id":"1803.08999","title":"LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image","created":"2018-03-23","cited_by_count":95},{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88},{"id":"2304.02009","title":"OrienterNet: Visual Localization in 2D Public Maps with Neural Matching","created":"2023-04-04","cited_by_count":84},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79},{"id":"1808.08473","title":"Human-centric Indoor Scene Synthesis Using Stochastic Grammar","created":"2018-08-25","cited_by_count":74},{"id":"2211.13287","title":"HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising","created":"2022-11-23","cited_by_count":73},{"id":"2304.08481","title":"Neural Map Prior for Autonomous Driving","created":"2023-04-17","cited_by_count":68},{"id":"2406.18524","title":"MultiDiff: Consistent Novel View Synthesis from a Single Image","created":"2024-06-26","cited_by_count":68},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56},{"id":"2104.00675","title":"In&Out : Diverse Image Outpainting via GAN Inversion","created":"2021-04-01","cited_by_count":55},{"id":"1912.12688","title":"Very Long Natural Scenery Image Prediction by Outpainting","created":"2019-12-29","cited_by_count":50},{"id":"1908.06702","title":"Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path","created":"2019-08-19","cited_by_count":36},{"id":"1804.00090","title":"FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans","created":"2018-03-31","cited_by_count":35},{"id":"2412.19948","title":"Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion Models","created":"2024-12-27","cited_by_count":33},{"id":"2303.08333","title":"DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception","created":"2023-03-15","cited_by_count":30},{"id":"2509.26618","title":"DA$^{2}$: Depth Anything in Any Direction","created":"2025-09-30","cited_by_count":25},{"id":"2306.13196","title":"DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability","created":"2023-06-22","cited_by_count":22},{"id":"2501.18913","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","created":"2025-01-31","cited_by_count":22},{"id":"2308.12963","title":"MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models","created":"2023-08-24","cited_by_count":21},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20},{"id":"1807.02192","title":"A Survey of Knowledge Representation in Service Robotics","created":"2018-07-05","cited_by_count":18},{"id":"2403.10454","title":"Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness","created":"2024-03-15","cited_by_count":17},{"id":"1705.10907","title":"Provably Safe Robot Navigation with Obstacle Uncertainty","created":"2017-05-31","cited_by_count":12},{"id":"2409.15590","title":"MapEx: Indoor Structure Exploration with Probabilistic Information Gain from Global Map Predictions","created":"2024-09-23","cited_by_count":12},{"id":"2102.11495","title":"Anytime Sampling for Autoregressive Models via Ordered Autoencoding","created":"2021-02-23","cited_by_count":11},{"id":"2503.11958","title":"CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts","created":"2025-03-15","cited_by_count":10},{"id":"2503.03921","title":"CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance","created":"2025-03-05","cited_by_count":9},{"id":"2403.11985","title":"SceneSense: Diffusion Models for 3D Occupancy Synthesis from Partial Observation","created":"2024-03-18","cited_by_count":8}],"next_cursor":"100"}