{"list":"other","total":88,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"1906.12320","title":"PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows","created":"2019-06-28","cited_by_count":488},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2306.17843","title":"Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors","created":"2023-06-30","cited_by_count":397},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2209.02646","title":"A Survey on Generative Diffusion Model","created":"2022-09-06","cited_by_count":240},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224},{"id":"2012.03762","title":"Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion","created":"2020-12-07","cited_by_count":223},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"2012.11409","title":"3D Object Detection with Pointformer","created":"2020-12-21","cited_by_count":194},{"id":"2312.03806","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","created":"2023-12-06","cited_by_count":189},{"id":"2008.10559","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","created":"2020-08-24","cited_by_count":188},{"id":"2406.07887","title":"An Empirical Study of Mamba-based Language Models","created":"2024-06-12","cited_by_count":186},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"id":"2402.05079","title":"Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation","created":"2024-02-07","cited_by_count":133},{"id":"2004.02122","title":"Anisotropic Convolutional Networks for 3D Semantic Scene Completion","created":"2020-04-05","cited_by_count":127},{"id":"2003.14052","title":"3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior","created":"2020-03-31","cited_by_count":126},{"id":"2206.12037","title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","created":"2022-06-24","cited_by_count":122},{"id":"2307.01831","title":"DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation","created":"2023-07-04","cited_by_count":110},{"id":"2012.09242","title":"S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds","created":"2020-12-16","cited_by_count":102},{"id":"2404.09502","title":"SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction","created":"2024-04-15","cited_by_count":96},{"id":"2309.14616","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","created":"2023-09-26","cited_by_count":90},{"id":"2402.05892","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","created":"2024-02-08","cited_by_count":84},{"id":"2403.16440","title":"RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection","created":"2024-03-25","cited_by_count":82},{"id":"2303.06884","title":"SCPNet: Semantic Scene Completion on Point Cloud","created":"2023-03-13","cited_by_count":80},{"id":"2311.01448","title":"UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation","created":"2023-11-02","cited_by_count":78},{"id":"2309.00610","title":"CityDreamer: Compositional Generative Model of Unbounded 3D Cities","created":"2023-09-01","cited_by_count":76},{"id":"2303.10735","title":"SKED: Sketch-guided Text-based 3D Editing","created":"2023-03-19","cited_by_count":73},{"id":"2403.06467","title":"Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy","created":"2024-03-11","cited_by_count":73},{"id":"2403.00762","title":"Point Cloud Mamba: Point Cloud Learning via State Space Model","created":"2024-03-01","cited_by_count":66},{"id":"2310.03602","title":"Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints","created":"2023-10-05","cited_by_count":60},{"id":"2403.15241","title":"IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection","created":"2024-03-22","cited_by_count":57},{"id":"1903.00620","title":"RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion","created":"2019-03-02","cited_by_count":55},{"id":"2104.03640","title":"Semantic Scene Completion via Integrating Instances and Scene in-the-Loop","created":"2021-04-08","cited_by_count":55},{"id":"2409.08215","title":"LT3SD: Latent Trees for 3D Scene Diffusion","created":"2024-09-12","cited_by_count":55},{"id":"2403.07773","title":"SemCity: Semantic Scene Generation with Triplane Diffusion","created":"2024-03-12","cited_by_count":53},{"id":"2405.13675","title":"Context and Geometry Aware Voxel Transformer for Semantic Scene Completion","created":"2024-05-22","cited_by_count":50},{"id":"2307.13537","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","created":"2023-07-25","cited_by_count":48},{"id":"2311.12085","title":"Pyramid Diffusion for Fine 3D Large Scene Generation","created":"2023-11-20","cited_by_count":44},{"id":"2404.11958","title":"Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation","created":"2024-04-18","cited_by_count":43},{"id":"2410.09049","title":"SceneCraft: Layout-Guided 3D Scene Generation","created":"2024-10-11","cited_by_count":41},{"id":"2410.18084","title":"DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes","created":"2024-10-23","cited_by_count":38},{"id":"2402.01771","title":"BlackMamba: Mixture of Experts for State-Space Models","created":"2024-02-01","cited_by_count":37},{"id":"2011.14744","title":"RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction","created":"2020-11-30","cited_by_count":36},{"id":"2308.02874","title":"Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation","created":"2023-08-05","cited_by_count":36},{"id":"2408.10195","title":"SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views","created":"2024-08-19","cited_by_count":35},{"id":"2301.00527","title":"Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data","created":"2023-01-02","cited_by_count":33},{"id":"2311.14495","title":"StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization","created":"2023-11-24","cited_by_count":30},{"id":"2311.04391","title":"3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features","created":"2023-11-07","cited_by_count":26},{"id":"2404.01174","title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","created":"2024-04-01","cited_by_count":25},{"id":"2404.11778","title":"CU-Mamba: Selective State Space Models with Channel Learning for Image Restoration","created":"2024-04-17","cited_by_count":24},{"id":"2412.01801","title":"SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation","created":"2024-12-02","cited_by_count":24},{"id":"2306.00519","title":"DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation","created":"2023-06-01","cited_by_count":23},{"id":"2307.03869","title":"Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generation","created":"2023-07-08","cited_by_count":14},{"id":"2403.11697","title":"Urban Scene Diffusion through Semantic Occupancy Map","created":"2024-03-18","cited_by_count":14},{"id":"2403.14121","title":"External Knowledge Enhanced 3D Scene Generation from Sketch","created":"2024-03-21","cited_by_count":9},{"id":"2501.07260","title":"Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion","created":"2025-01-13","cited_by_count":9},{"id":"2410.20508","title":"Referring Human Pose and Mask Estimation in the Wild","created":"2024-10-27","cited_by_count":6},{"id":"2503.21449","title":"Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving","created":"2025-03-27","cited_by_count":5}],"next_cursor":null}