{"list":"other","total":56,"rows":[{"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"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":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2212.05231","title":"NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction","created":"2022-12-10","cited_by_count":314},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"id":"2312.02069","title":"GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians","created":"2023-12-04","cited_by_count":260},{"id":"2410.24207","title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","created":"2024-10-31","cited_by_count":248},{"id":"2105.01859","title":"Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors","created":"2021-05-05","cited_by_count":246},{"id":"2505.23716","title":"AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views","created":"2025-05-29","cited_by_count":243},{"id":"2312.02134","title":"GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians","created":"2023-12-04","cited_by_count":191},{"id":"2402.03307","title":"4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes","created":"2024-02-05","cited_by_count":189},{"id":"2305.06356","title":"HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion","created":"2023-05-10","cited_by_count":161},{"id":"2403.01444","title":"3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos","created":"2024-03-03","cited_by_count":160},{"id":"2104.14786","title":"Editable Free-viewpoint Video Using a Layered Neural Representation","created":"2021-04-30","cited_by_count":148},{"id":"2108.11515","title":"Robust High-Resolution Video Matting with Temporal Guidance","created":"2021-08-25","cited_by_count":137},{"id":"2206.10589","title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","created":"2022-06-21","cited_by_count":121},{"id":"2112.02789","title":"HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs","created":"2021-12-06","cited_by_count":112},{"id":"2404.06270","title":"3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis","created":"2024-04-09","cited_by_count":109},{"id":"2307.10173","title":"DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering","created":"2023-07-19","cited_by_count":103},{"id":"2403.11447","title":"Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction","created":"2024-03-18","cited_by_count":100},{"id":"2310.11448","title":"4K4D: Real-Time 4D View Synthesis at 4K Resolution","created":"2023-10-17","cited_by_count":91},{"id":"2312.04558","title":"MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar","created":"2023-12-07","cited_by_count":89},{"id":"1912.04302","title":"DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data","created":"2019-12-09","cited_by_count":77},{"id":"2304.04452","title":"Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos","created":"2023-04-10","cited_by_count":77},{"id":"2211.13206","title":"AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels","created":"2022-11-23","cited_by_count":73},{"id":"2303.15108","title":"High-fidelity 3D Human Digitization from Single 2K Resolution Images","created":"2023-03-27","cited_by_count":70},{"id":"2412.09608","title":"Representing Long Volumetric Video with Temporal Gaussian Hierarchy","created":"2024-12-12","cited_by_count":58},{"id":"2506.05348","title":"FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction","created":"2025-06-05","cited_by_count":54},{"id":"2106.03798","title":"DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Rendering","created":"2021-06-07","cited_by_count":52},{"id":"2406.00434","title":"MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors","created":"2024-06-01","cited_by_count":51},{"id":"2410.20815","title":"Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting","created":"2024-10-28","cited_by_count":49},{"id":"2503.16979","title":"Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting","created":"2025-03-21","cited_by_count":36},{"id":"2407.08414","title":"MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos","created":"2024-07-11","cited_by_count":34},{"id":"2503.01610","title":"Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior","created":"2025-03-03","cited_by_count":31},{"id":"2409.13648","title":"V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians","created":"2024-09-20","cited_by_count":29},{"id":"2411.08879","title":"4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization","created":"2024-11-13","cited_by_count":28},{"id":"2312.01407","title":"VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams","created":"2023-12-03","cited_by_count":22},{"id":"2411.11363","title":"GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views","created":"2024-11-18","cited_by_count":22},{"id":"2503.07946","title":"7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting","created":"2025-03-11","cited_by_count":18},{"id":"2411.14847","title":"Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly 4D Reconstruction","created":"2024-11-22","cited_by_count":14},{"id":"2512.11782","title":"MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator","created":"2025-12-12","cited_by_count":7},{"id":"2602.02989","title":"SharpTimeGS: Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulation","created":"2026-02-03","cited_by_count":1},{"id":"2606.29333","title":"HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video","created":"2026-06-28","cited_by_count":1}],"next_cursor":null}