{"list":"other","total":82,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"id":"2311.16493","title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","created":"2023-11-27","cited_by_count":667},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2104.06405","title":"BARF: Bundle-Adjusting Neural Radiance Fields","created":"2021-04-13","cited_by_count":642},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"id":"2012.09161","title":"Learning Continuous Image Representation with Local Implicit Image Function","created":"2020-12-16","cited_by_count":552},{"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":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2310.10642","title":"Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting","created":"2023-10-16","cited_by_count":476},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","cited_by_count":364},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2312.00451","title":"FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting","created":"2023-12-01","cited_by_count":279},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2012.09855","title":"Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image","created":"2020-12-17","cited_by_count":243},{"id":"2212.07388","title":"NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior","created":"2022-12-14","cited_by_count":235},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"2312.07504","title":"COLMAP-Free 3D Gaussian Splatting","created":"2023-12-12","cited_by_count":193},{"id":"2309.17102","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","created":"2023-09-29","cited_by_count":185},{"id":"2311.13398","title":"Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images","created":"2023-11-22","cited_by_count":173},{"id":"2405.04233","title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","created":"2024-05-07","cited_by_count":160},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2312.00112","title":"DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting","created":"2023-11-30","cited_by_count":124},{"id":"2403.16292","title":"latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction","created":"2024-03-24","cited_by_count":118},{"id":"2005.04551","title":"Epipolar Transformers","created":"2020-05-10","cited_by_count":117},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108},{"id":"2408.13770","title":"TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers","created":"2024-08-25","cited_by_count":75},{"id":"2204.07151","title":"Deformable Sprites for Unsupervised Video Decomposition","created":"2022-04-14","cited_by_count":61},{"id":"2311.12897","title":"A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis","created":"2023-11-21","cited_by_count":59},{"id":"2409.08270","title":"FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally","created":"2024-09-12","cited_by_count":58},{"id":"1904.10631","title":"Low-Memory Neural Network Training: A Technical Report","created":"2019-04-24","cited_by_count":57},{"id":"2403.18795","title":"Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction","created":"2024-03-27","cited_by_count":56},{"id":"2410.08261","title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","created":"2024-10-10","cited_by_count":56},{"id":"2204.07346","title":"MVSTER: Epipolar Transformer for Efficient Multi-View Stereo","created":"2022-04-15","cited_by_count":50},{"id":"2405.18426","title":"GFlow: Recovering 4D World from Monocular Video","created":"2024-05-28","cited_by_count":46},{"id":"2406.13870","title":"Splatter a Video: Video Gaussian Representation for Versatile Processing","created":"2024-06-19","cited_by_count":31},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27},{"id":"2406.06367","title":"MVGamba: Unify 3D Content Generation as State Space Sequence Modeling","created":"2024-06-10","cited_by_count":23},{"id":"2404.04562","title":"Diffusion Time-step Curriculum for One Image to 3D Generation","created":"2024-04-06","cited_by_count":21},{"id":"2010.06192","title":"Revisiting BFloat16 Training","created":"2020-10-13","cited_by_count":17},{"id":"2406.18198","title":"VDG: Vision-Only Dynamic Gaussian for Driving Simulation","created":"2024-06-26","cited_by_count":16},{"id":"2308.09694","title":"Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition","created":"2023-08-18","cited_by_count":13},{"id":"2205.07230","title":"Video Frame Interpolation with Transformer","created":"2022-05-15","cited_by_count":2}],"next_cursor":null}