{"list":"other","total":61,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"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":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"id":"2302.04264","title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development","created":"2023-02-08","cited_by_count":600},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"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":"1911.11907","title":"GhostNet: More Features from Cheap Operations","created":"2019-11-27","cited_by_count":410},{"id":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","cited_by_count":364},{"id":"1712.00080","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","created":"2017-11-30","cited_by_count":326},{"id":"2210.04628","title":"Novel View Synthesis with Diffusion Models","created":"2022-10-06","cited_by_count":300},{"id":"1902.10556","title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","created":"2019-02-27","cited_by_count":254},{"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":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"id":"2212.07388","title":"NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior","created":"2022-12-14","cited_by_count":235},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"2212.00792","title":"SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction","created":"2022-12-01","cited_by_count":216},{"id":"1708.01692","title":"Video Frame Interpolation via Adaptive Separable Convolution","created":"2017-08-05","cited_by_count":213},{"id":"2312.02155","title":"GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis","created":"2023-12-04","cited_by_count":170},{"id":"1912.08329","title":"Cost Volume Pyramid Based Depth Inference for Multi-View Stereo","created":"2019-12-18","cited_by_count":154},{"id":"1911.12012","title":"Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness","created":"2019-11-27","cited_by_count":151},{"id":"2112.01517","title":"Efficient Neural Radiance Fields for Interactive Free-viewpoint Video","created":"2021-12-02","cited_by_count":150},{"id":"2111.15246","title":"Hallucinated Neural Radiance Fields in the Wild","created":"2021-11-30","cited_by_count":130},{"id":"2311.18159","title":"CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization","created":"2023-11-30","cited_by_count":130},{"id":"2007.12622","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","created":"2020-07-17","cited_by_count":118},{"id":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117},{"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":"2412.00578","title":"Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives","created":"2024-11-30","cited_by_count":95},{"id":"2403.19495","title":"CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians","created":"2024-03-28","cited_by_count":62},{"id":"1804.00884","title":"PhaseNet for Video Frame Interpolation","created":"2018-04-03","cited_by_count":61},{"id":"2503.14445","title":"Bolt3D: Generating 3D Scenes in Seconds","created":"2025-03-18","cited_by_count":59},{"id":"2312.02963","title":"MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures","created":"2023-12-05","cited_by_count":54},{"id":"2012.08270","title":"FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion","created":"2020-12-15","cited_by_count":45},{"id":"2211.12905","title":"GhostNetV2: Enhance Cheap Operation with Long-Range Attention","created":"2022-11-23","cited_by_count":44},{"id":"1603.06041","title":"Learning Image Matching by Simply Watching Video","created":"2016-03-19","cited_by_count":41},{"id":"2203.03949","title":"RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering","created":"2022-03-08","cited_by_count":30},{"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":"2503.15831","title":"EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation","created":"2025-03-20","cited_by_count":19},{"id":"2410.16271","title":"FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors","created":"2024-10-21","cited_by_count":18},{"id":"2411.07765","title":"Novel View Synthesis with Pixel-Space Diffusion Models","created":"2024-11-12","cited_by_count":16},{"id":"2112.00336","title":"Multi-View Stereo with Transformer","created":"2021-12-01","cited_by_count":14},{"id":"2412.11365","title":"BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions","created":"2024-12-16","cited_by_count":13},{"id":"2501.18804","title":"Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion","created":"2025-01-30","cited_by_count":12},{"id":"2203.15427","title":"Long-term Video Frame Interpolation via Feature Propagation","created":"2022-03-29","cited_by_count":8},{"id":"2504.00380","title":"Hierarchical Flow Diffusion for Efficient Frame Interpolation","created":"2025-04-01","cited_by_count":7},{"id":"2409.08613","title":"Dense Point Clouds Matter: Dust-GS for Scene Reconstruction from Sparse Viewpoints","created":"2024-09-13","cited_by_count":6},{"id":"2312.08892","title":"VaLID: Variable-Length Input Diffusion for Novel View Synthesis","created":"2023-12-14","cited_by_count":4},{"id":"2312.08594","title":"CT-MVSNet: Efficient Multi-View Stereo with Cross-scale Transformer","created":"2023-12-14","cited_by_count":2},{"id":"2508.14892","title":"Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds","created":"2025-08-20","cited_by_count":2}],"next_cursor":null}