{"list":"other","total":90,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2112.05131","title":"Plenoxels: Radiance Fields without Neural Networks","created":"2021-12-09","cited_by_count":1613},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"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":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"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":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2111.11215","title":"Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction","created":"2021-11-22","cited_by_count":964},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2103.15595","title":"MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo","created":"2021-03-29","cited_by_count":740},{"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":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"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":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"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":"2103.13744","title":"KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs","created":"2021-03-25","cited_by_count":673},{"id":"2309.03453","title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","created":"2023-09-07","cited_by_count":645},{"id":"2302.04264","title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development","created":"2023-02-08","cited_by_count":600},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"1912.06378","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","created":"2019-12-13","cited_by_count":417},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"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":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"id":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","cited_by_count":227},{"id":"2307.01097","title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion","created":"2023-07-03","cited_by_count":212},{"id":"2107.13421","title":"Neural Rays for Occlusion-aware Image-based Rendering","created":"2021-07-28","cited_by_count":192},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2408.13912","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-08-25","cited_by_count":178},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169},{"id":"1912.08329","title":"Cost Volume Pyramid Based Depth Inference for Multi-View Stereo","created":"2019-12-18","cited_by_count":154},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139},{"id":"2407.07090","title":"3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes","created":"2024-07-09","cited_by_count":139},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130},{"id":"2207.10662","title":"Generalizable Patch-Based Neural Rendering","created":"2022-07-21","cited_by_count":122},{"id":"2303.15951","title":"F$^{2}$-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories","created":"2023-03-28","cited_by_count":118},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116},{"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":"2112.09687","title":"Light Field Neural Rendering","created":"2021-12-17","cited_by_count":108},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2304.08463","title":"Learning to Render Novel Views from Wide-Baseline Stereo Pairs","created":"2023-04-17","cited_by_count":104},{"id":"2303.13791","title":"Progressively Optimized Local Radiance Fields for Robust View Synthesis","created":"2023-03-24","cited_by_count":103},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"id":"2402.03908","title":"EscherNet: A Generative Model for Scalable View Synthesis","created":"2024-02-06","cited_by_count":95},{"id":"2402.12712","title":"MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction","created":"2024-02-20","cited_by_count":95},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89},{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","cited_by_count":77},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77},{"id":"2412.03526","title":"Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos","created":"2024-12-04","cited_by_count":49},{"id":"2312.07246","title":"Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs","created":"2023-12-12","cited_by_count":37},{"id":"2412.04459","title":"Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering","created":"2024-12-05","cited_by_count":35},{"id":"2502.01157","title":"Radiant Foam: Real-Time Differentiable Ray Tracing","created":"2025-02-03","cited_by_count":34},{"id":"2508.14041","title":"LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos","created":"2025-08-19","cited_by_count":24},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22},{"id":"2501.16312","title":"LinPrim: Linear Primitives for Differentiable Volumetric Rendering","created":"2025-01-27","cited_by_count":21},{"id":"2510.13063","title":"True Self-Supervised Novel View Synthesis is Transferable","created":"2025-10-15","cited_by_count":15},{"id":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","cited_by_count":13},{"id":"2602.20160","title":"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction","created":"2026-02-23","cited_by_count":12},{"id":"2201.05023","title":"Stereo Magnification with Multi-Layer Images","created":"2022-01-13","cited_by_count":11},{"id":"2502.07754","title":"MeshSplats: Mesh-Based Rendering with Gaussian Splatting Initialization","created":"2025-02-11","cited_by_count":9},{"id":"2602.21341","title":"Scaling View Synthesis Transformers","created":"2026-02-24","cited_by_count":9},{"id":"2602.06478","title":"Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention","created":"2026-02-06","cited_by_count":6},{"id":"2507.08776","title":"CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering","created":"2025-07-11","cited_by_count":5},{"id":"2512.10267","title":"Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction","created":"2025-12-11","cited_by_count":4}],"next_cursor":null}