{"list":"other","total":59,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"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":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163},{"id":"1701.08493","title":"A Survey of Structure from Motion","created":"2017-01-30","cited_by_count":158},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154},{"id":"2408.16767","title":"ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model","created":"2024-08-29","cited_by_count":143},{"id":"2412.06974","title":"MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds","created":"2024-12-09","cited_by_count":141},{"id":"2411.04928","title":"DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion","created":"2024-11-07","cited_by_count":140},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114},{"id":"2506.04225","title":"Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation","created":"2025-06-04","cited_by_count":101},{"id":"2412.12091","title":"Wonderland: Navigating 3D Scenes from a Single Image","created":"2024-12-16","cited_by_count":99},{"id":"2503.10592","title":"CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models","created":"2025-03-13","cited_by_count":98},{"id":"2503.18945","title":"Aether: Geometric-Aware Unified World Modeling","created":"2025-03-24","cited_by_count":97},{"id":"2403.06738","title":"V3D: Video Diffusion Models are Effective 3D Generators","created":"2024-03-11","cited_by_count":89},{"id":"2504.07961","title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","created":"2025-04-10","cited_by_count":67},{"id":"2412.01821","title":"World-consistent Video Diffusion with Explicit 3D Modeling","created":"2024-12-02","cited_by_count":65},{"id":"2311.17138","title":"Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now","created":"2023-11-28","cited_by_count":61},{"id":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49},{"id":"2502.07685","title":"Matrix3D: Large Photogrammetry Model All-in-One","created":"2025-02-11","cited_by_count":40},{"id":"2310.06836","title":"A General Protocol to Probe Large Vision Models for 3D Physical Understanding","created":"2023-10-10","cited_by_count":32},{"id":"2412.09606","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting","created":"2024-12-12","cited_by_count":27},{"id":"2505.11992","title":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","created":"2025-05-17","cited_by_count":16},{"id":"2409.05862","title":"Evaluating Multiview Object Consistency in Humans and Image Models","created":"2024-09-09","cited_by_count":13},{"id":"2410.10799","title":"Towards Foundation Models for 3D Vision: How Close Are We?","created":"2024-10-14","cited_by_count":13},{"id":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","cited_by_count":10},{"id":"2501.01409","title":"JOG3R: Towards 3D-Consistent Video Generators","created":"2025-01-02","cited_by_count":9},{"id":"2511.22121","title":"Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation","created":"2025-11-27","cited_by_count":2}],"next_cursor":null}