{"list":"other","total":88,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"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":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"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":"2109.02497","title":"Voxel Transformer for 3D Object Detection","created":"2021-09-06","cited_by_count":247},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"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":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202},{"id":"2008.10559","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","created":"2020-08-24","cited_by_count":188},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2405.17429","title":"GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction","created":"2024-05-27","cited_by_count":157},{"id":"1911.12676","title":"xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation","created":"2019-11-28","cited_by_count":129},{"id":"2303.17597","title":"Robo3D: Towards Robust and Reliable 3D Perception against Corruptions","created":"2023-03-30","cited_by_count":129},{"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":"2306.09347","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","created":"2023-06-15","cited_by_count":125},{"id":"2501.04003","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","created":"2025-01-07","cited_by_count":122},{"id":"2305.03045","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","created":"2023-05-04","cited_by_count":109},{"id":"2203.10314","title":"Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds","created":"2022-03-19","cited_by_count":102},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94},{"id":"2207.00026","title":"LaserMix for Semi-Supervised LiDAR Semantic Segmentation","created":"2022-06-30","cited_by_count":93},{"id":"2306.15670","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","created":"2023-06-27","cited_by_count":90},{"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":"2303.06884","title":"SCPNet: Semantic Scene Completion on Point Cloud","created":"2023-03-13","cited_by_count":80},{"id":"2011.09141","title":"Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data","created":"2020-11-18","cited_by_count":74},{"id":"2301.08739","title":"FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer","created":"2023-01-20","cited_by_count":73},{"id":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72},{"id":"2111.02444","title":"Panoptic 3D Scene Reconstruction From a Single RGB Image","created":"2021-11-03","cited_by_count":70},{"id":"2112.01988","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","created":"2021-12-03","cited_by_count":67},{"id":"2412.04383","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","created":"2024-12-05","cited_by_count":67},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2403.12409","title":"ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance","created":"2024-03-19","cited_by_count":59},{"id":"1903.00620","title":"RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion","created":"2019-03-02","cited_by_count":55},{"id":"2306.03899","title":"Towards Label-free Scene Understanding by Vision Foundation Models","created":"2023-06-06","cited_by_count":54},{"id":"2405.05258","title":"Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving","created":"2024-05-08","cited_by_count":54},{"id":"2312.04484","title":"FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation","created":"2023-12-07","cited_by_count":50},{"id":"2311.18610","title":"DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image","created":"2023-11-30","cited_by_count":48},{"id":"2207.08656","title":"Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes","created":"2022-07-18","cited_by_count":44},{"id":"2403.08766","title":"MonoOcc: Digging into Monocular Semantic Occupancy Prediction","created":"2024-03-13","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":"2405.17426","title":"Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving","created":"2024-05-27","cited_by_count":41},{"id":"2407.04049","title":"Occupancy as Set of Points","created":"2024-07-04","cited_by_count":38},{"id":"2410.18084","title":"DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes","created":"2024-10-23","cited_by_count":38},{"id":"2405.04299","title":"ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers","created":"2024-05-07","cited_by_count":37},{"id":"2410.15971","title":"Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly","created":"2024-10-21","cited_by_count":35},{"id":"2407.06190","title":"4D Contrastive Superflows are Dense 3D Representation Learners","created":"2024-07-08","cited_by_count":33},{"id":"2407.02077","title":"Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion","created":"2024-07-02","cited_by_count":32},{"id":"2407.11730","title":"Monocular Occupancy Prediction for Scalable Indoor Scenes","created":"2024-07-16","cited_by_count":31},{"id":"2303.16094","title":"LinK: Linear Kernel for LiDAR-based 3D Perception","created":"2023-03-28","cited_by_count":26},{"id":"2403.17009","title":"Is Your LiDAR Placement Optimized for 3D Scene Understanding?","created":"2024-03-25","cited_by_count":26},{"id":"2405.01538","title":"Multi-Space Alignments Towards Universal LiDAR Segmentation","created":"2024-05-02","cited_by_count":25},{"id":"2307.03244","title":"PSDR-Room: Single Photo to Scene using Differentiable Rendering","created":"2023-07-06","cited_by_count":23},{"id":"2507.22825","title":"DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion","created":"2025-07-30","cited_by_count":23},{"id":"2306.00965","title":"BUOL: A Bottom-Up Framework with Occupancy-aware Lifting for Panoptic 3D Scene Reconstruction From A Single Image","created":"2023-06-01","cited_by_count":20},{"id":"2501.04004","title":"LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes","created":"2025-01-07","cited_by_count":19},{"id":"2507.17665","title":"Perspective-Invariant 3D Object Detection","created":"2025-07-23","cited_by_count":18},{"id":"2508.03692","title":"LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences","created":"2025-08-05","cited_by_count":17},{"id":"2403.10001","title":"Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation","created":"2024-03-15","cited_by_count":15},{"id":"2403.15173","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","created":"2024-03-22","cited_by_count":15},{"id":"2504.16023","title":"PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning","created":"2025-04-22","cited_by_count":14},{"id":"2501.04005","title":"LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving","created":"2025-01-07","cited_by_count":12},{"id":"2511.01755","title":"3EED: Ground Everything Everywhere in 3D","created":"2025-11-03","cited_by_count":12},{"id":"2505.22643","title":"SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding","created":"2025-05-28","cited_by_count":10},{"id":"2508.03691","title":"La La LiDAR: Large-Scale Layout Generation from LiDAR Data","created":"2025-08-05","cited_by_count":10},{"id":"2405.15170","title":"Label-efficient Semantic Scene Completion with Scribble Annotations","created":"2024-05-24","cited_by_count":9},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8},{"id":"2507.05260","title":"Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations","created":"2025-07-07","cited_by_count":7},{"id":"2505.24634","title":"NUC-Net: Non-uniform Cylindrical Partition Network for Efficient LiDAR Semantic Segmentation","created":"2025-05-30","cited_by_count":5},{"id":"2508.03690","title":"Veila: Panoramic LiDAR Generation from a Monocular RGB Image","created":"2025-08-05","cited_by_count":5},{"id":"2411.16129","title":"Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion","created":"2024-11-25","cited_by_count":4},{"id":"2503.19912","title":"Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining","created":"2025-03-25","cited_by_count":4},{"id":"2512.24385","title":"Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems","created":"2025-12-30","cited_by_count":4},{"id":"2503.05086","title":"Fake It To Make It: Virtual Multiviews to Enhance Monocular Indoor Semantic Scene Completion","created":"2025-03-07","cited_by_count":2},{"id":"2511.11074","title":"Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image","created":"2025-11-14","cited_by_count":1}],"next_cursor":null}