{"total":177,"rows":[{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422,"area":null},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838,"area":"mllm"},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770,"area":null},{"id":"2405.14832","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","created":"2024-05-23","cited_by_count":210,"area":"diffusion"},{"id":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173,"area":null},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154,"area":"diffusion"},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139,"area":"lr"},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89,"area":null},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71,"area":null},{"id":"2506.01946","title":"3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding","created":"2025-06-02","cited_by_count":70,"area":"lr"},{"id":"2410.16499","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects","created":"2024-10-21","cited_by_count":69,"area":null},{"id":"2406.20055","title":"SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":61,"area":null},{"id":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61,"area":null},{"id":"2501.09466","title":"DEFOM-Stereo: Depth Foundation Model Based Stereo Matching","created":"2025-01-16","cited_by_count":52,"area":null},{"id":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49,"area":null},{"id":"2505.00788","title":"SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models","created":"2025-05-01","cited_by_count":38,"area":"lr"},{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2406.15333","title":"GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation","created":"2024-06-21","cited_by_count":36,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2406.09292","title":"Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models","created":"2024-06-13","cited_by_count":30,"area":"diffusion"},{"id":"2412.09072","title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","created":"2024-12-12","cited_by_count":30,"area":null},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"area":null},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2510.12764","title":"AnyUp: Universal Feature Upsampling","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2412.09606","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting","created":"2024-12-12","cited_by_count":27,"area":null},{"id":"2406.09613","title":"ImageNet3D: Towards General-Purpose Object-Level 3D Understanding","created":"2024-06-13","cited_by_count":25,"area":null},{"id":"2503.04919","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","created":"2025-03-06","cited_by_count":25,"area":"lr"},{"id":"2506.21876","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation","created":"2025-06-27","cited_by_count":24,"area":"wm"},{"id":"2504.14032","title":"LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models","created":"2025-04-18","cited_by_count":23,"area":null},{"id":"2410.01680","title":"PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation","created":"2024-10-02","cited_by_count":21,"area":"distill"},{"id":"2512.04021","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","created":"2025-12-03","cited_by_count":21,"area":null},{"id":"2412.14580","title":"DiffSim: Taming Diffusion Models for Evaluating Visual Similarity","created":"2024-12-19","cited_by_count":20,"area":"diffusion"},{"id":"2411.17385","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","created":"2024-11-26","cited_by_count":19,"area":null},{"id":"2406.04138","title":"The 3D-PC: a benchmark for visual perspective taking in humans and machines","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2407.17310","title":"LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering","created":"2024-07-24","cited_by_count":16,"area":null},{"id":"2408.11054","title":"Near, far: Patch-ordering enhances vision foundation models' scene understanding","created":"2024-08-20","cited_by_count":15,"area":null},{"id":"2603.22275","title":"Repurposing Geometric Foundation Models for Multi-view Diffusion","created":"2026-03-23","cited_by_count":15,"area":"diffusion"},{"id":"2408.13575","title":"Can Visual Foundation Models Achieve Long-term Point Tracking?","created":"2024-08-24","cited_by_count":14,"area":null},{"id":"2411.19458","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","created":"2024-11-29","cited_by_count":14,"area":null},{"id":"2409.05862","title":"Evaluating Multiview Object Consistency in Humans and Image Models","created":"2024-09-09","cited_by_count":13,"area":null},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2410.10799","title":"Towards Foundation Models for 3D Vision: How Close Are We?","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2503.16707","title":"Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding","created":"2025-03-20","cited_by_count":13,"area":"mllm"},{"id":"2507.08254","title":"Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models","created":"2025-07-11","cited_by_count":13,"area":null},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2409.11682","title":"SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation","created":"2024-09-18","cited_by_count":12,"area":"diffusion"},{"id":"2503.21747","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","created":"2025-03-27","cited_by_count":12,"area":null},{"id":"2601.17237","title":"C-RADIOv4 (Tech Report)","created":"2026-01-24","cited_by_count":12,"area":null},{"id":"2411.19492","title":"Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2504.06752","title":"Compass Control: Multi Object Orientation Control for Text-to-Image Generation","created":"2025-04-09","cited_by_count":11,"area":"diffusion"},{"id":"2508.05254","title":"CF3: Compact and Fast 3D Feature Fields","created":"2025-08-07","cited_by_count":11,"area":null},{"id":"2512.19949","title":"How Much 3D Do Video Foundation Models Encode?","created":"2025-12-23","cited_by_count":11,"area":null},{"id":"2411.19322","title":"SAMa: Material-aware 3D Selection and Segmentation","created":"2024-11-28","cited_by_count":10,"area":null},{"id":"2512.03045","title":"CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2409.16178","title":"SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image","created":"2024-09-24","cited_by_count":9,"area":null},{"id":"2410.11187","title":"Multiview Scene Graph","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2412.09585","title":"Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation","created":"2024-12-12","cited_by_count":9,"area":"mllm"},{"id":"2501.01409","title":"JOG3R: Towards 3D-Consistent Video Generators","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2512.14671","title":"ART: Articulated Reconstruction Transformer","created":"2025-12-16","cited_by_count":9,"area":null},{"id":"2609.00111","title":"Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving","created":"2026-08-31","cited_by_count":9,"area":"mllm"},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2411.17474","title":"Probing the Mid-level Vision Capabilities of Self-Supervised Learning","created":"2024-11-25","cited_by_count":7,"area":null},{"id":"2502.20316","title":"Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2408.06721","title":"Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities","created":"2024-08-13","cited_by_count":6,"area":"mllm"},{"id":"2409.10228","title":"Robust Bird's Eye View Segmentation by Adapting DINOv2","created":"2024-09-16","cited_by_count":6,"area":null},{"id":"2502.16025","title":"FeatSharp: Your Vision Model Features, Sharper","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2508.00746","title":"GECO: Geometrically Consistent Embedding with Lightspeed Inference","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2509.24288","title":"ASIA: Adaptive 3D Segmentation using Few Image Annotations","created":"2025-09-29","cited_by_count":6,"area":"diffusion"},{"id":"2510.09320","title":"Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2511.18452","title":"NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering","created":"2025-11-23","cited_by_count":6,"area":null},{"id":"2406.12671","title":"GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2412.19920","title":"Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models","created":"2024-12-27","cited_by_count":5,"area":null},{"id":"2503.15470","title":"EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2506.09883","title":"3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2506.09935","title":"LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2511.17309","title":"MuM: Multi-View Masked Image Modeling for 3D Vision","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2406.20099","title":"Odd-One-Out: Anomaly Detection by Comparing with Neighbors","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2407.20908","title":"Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering","created":"2024-07-30","cited_by_count":4,"area":null},{"id":"2410.21708","title":"Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation","created":"2024-10-29","cited_by_count":4,"area":"diffusion"},{"id":"2501.16458","title":"BiFold: Bimanual Cloth Folding with Language Guidance","created":"2025-01-27","cited_by_count":4,"area":null},{"id":"2503.15897","title":"Learning 3D Scene Analogies with Neural Contextual Scene Maps","created":"2025-03-20","cited_by_count":4,"area":null},{"id":"2506.06846","title":"Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Styles","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2511.18991","title":"View-Consistent Diffusion Representations for 3D-Consistent Video Generation","created":"2025-11-24","cited_by_count":4,"area":"diffusion"},{"id":"2602.23359","title":"SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation","created":"2026-02-26","cited_by_count":4,"area":null},{"id":"2602.24181","title":"A Mixed Diet Makes DINO An Omnivorous Vision Encoder","created":"2026-02-27","cited_by_count":4,"area":null},{"id":"2410.16259","title":"Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2511.18115","title":"Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-training","created":"2025-11-22","cited_by_count":3,"area":null},{"id":"2601.18923","title":"DeFM: Learning Foundation Representations from Depth for Robotics","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2602.04880","title":"Capturing Visual Environment Structure Correlates with Control Performance","created":"2026-02-04","cited_by_count":3,"area":"vla"},{"id":"2604.18267","title":"MARCO: Navigating the Unseen Space of Semantic Correspondence","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2605.16745","title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","created":"2026-05-16","cited_by_count":3,"area":"mllm"},{"id":"2606.09646","title":"How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2504.19718","title":"Pixels2Points: Fusing 2D and 3D Features for Facial Skin Segmentation","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2506.08194","title":"GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra","created":"2025-06-09","cited_by_count":2,"area":"lr"},{"id":"2506.09885","title":"The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2508.13601","title":"Unleashing Semantic and Geometric Priors for 3D Scene Completion","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2509.09547","title":"Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders","created":"2025-09-11","cited_by_count":2,"area":"diffusion"}],"next_cursor":"100"}