{"list":"other","total":52,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2112.05131","title":"Plenoxels: Radiance Fields without Neural Networks","created":"2021-12-09","cited_by_count":1613},{"id":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2103.14024","title":"PlenOctrees for Real-time Rendering of Neural Radiance Fields","created":"2021-03-25","cited_by_count":905},{"id":"2103.13744","title":"KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs","created":"2021-03-25","cited_by_count":673},{"id":"2311.16493","title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","created":"2023-11-27","cited_by_count":667},{"id":"2201.08845","title":"Point-NeRF: Point-based Neural Radiance Fields","created":"2022-01-21","cited_by_count":503},{"id":"2103.14645","title":"Baking Neural Radiance Fields for Real-Time View Synthesis","created":"2021-03-26","cited_by_count":468},{"id":"2311.13681","title":"Compact 3D Gaussian Representation for Radiance Field","created":"2023-11-22","cited_by_count":372},{"id":"2111.13679","title":"NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images","created":"2021-11-26","cited_by_count":336},{"id":"2302.14859","title":"BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis","created":"2023-02-28","cited_by_count":221},{"id":"2403.10516","title":"FeatUp: A Model-Agnostic Framework for Features at Any Resolution","created":"2024-03-15","cited_by_count":116},{"id":"2309.15426","title":"NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions","created":"2023-09-27","cited_by_count":65},{"id":"2304.09987","title":"Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra","created":"2023-04-19","cited_by_count":57},{"id":"2307.10664","title":"Lighting up NeRF via Unsupervised Decomposition and Enhancement","created":"2023-07-20","cited_by_count":40},{"id":"2308.01738","title":"Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution","created":"2023-08-03","cited_by_count":39},{"id":"2312.09093","title":"Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption","created":"2023-12-14","cited_by_count":35},{"id":"2406.00448","title":"Bilateral Guided Radiance Field Processing","created":"2024-06-01","cited_by_count":28},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28},{"id":"2504.03193","title":"Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation","created":"2025-04-04","cited_by_count":24},{"id":"2403.07408","title":"NightHaze: Nighttime Image Dehazing via Self-Prior Learning","created":"2024-03-12","cited_by_count":23},{"id":"2503.20211","title":"Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors","created":"2025-03-26","cited_by_count":22},{"id":"2401.00729","title":"NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction","created":"2024-01-01","cited_by_count":20},{"id":"2403.12884","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","created":"2024-03-19","cited_by_count":18},{"id":"2502.15224","title":"Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery","created":"2025-02-21","cited_by_count":16},{"id":"2312.17492","title":"HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping","created":"2023-12-29","cited_by_count":10},{"id":"2602.18735","title":"LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency","created":"2026-02-21","cited_by_count":9},{"id":"2503.19263","title":"DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning","created":"2025-03-25","cited_by_count":8},{"id":"2505.13050","title":"RGB-to-Polarization Estimation: A New Task and Benchmark Study","created":"2025-05-19","cited_by_count":8},{"id":"2503.18853","title":"3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image","created":"2025-03-24","cited_by_count":7},{"id":"2602.15383","title":"Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation","created":"2026-02-17","cited_by_count":6},{"id":"2510.03110","title":"GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion","created":"2025-10-03","cited_by_count":5},{"id":"2603.17680","title":"WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models","created":"2026-03-18","cited_by_count":5},{"id":"2503.08073","title":"Seeing Beyond Haze: Generative Nighttime Image Dehazing","created":"2025-03-11","cited_by_count":4},{"id":"2509.00665","title":"ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation","created":"2025-08-31","cited_by_count":4},{"id":"2510.17719","title":"OmniRaindrop: A Comprehensive Benchmark for Dual-Focused Raindrop Removal under Day and Night Scenes","created":"2025-10-20","cited_by_count":4},{"id":"2603.16506","title":"VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations","created":"2026-03-17","cited_by_count":3},{"id":"2604.01857","title":"Enhanced Polarization Locking in VCSELs","created":"2026-04-02","cited_by_count":1}],"next_cursor":null}