{"total":119,"rows":[{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286,"area":"diffusion"},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205,"area":null},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166,"area":"diffusion"},{"id":"2303.17597","title":"Robo3D: Towards Robust and Reliable 3D Perception against Corruptions","created":"2023-03-30","cited_by_count":129,"area":null},{"id":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2506.06659","title":"DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning","created":"2025-06-07","cited_by_count":94,"area":null},{"id":"2409.11355","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","created":"2024-09-17","cited_by_count":83,"area":"diffusion"},{"id":"2505.09358","title":"Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis","created":"2025-05-14","cited_by_count":78,"area":"diffusion"},{"id":"2403.06090","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","created":"2024-03-10","cited_by_count":74,"area":"diffusion"},{"id":"2404.07204","title":"BRAVE: Broadening the visual encoding of vision-language models","created":"2024-04-10","cited_by_count":69,"area":"mllm"},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67,"area":null},{"id":"2309.17261","title":"Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors","created":"2023-09-29","cited_by_count":64,"area":"diffusion"},{"id":"2306.05401","title":"RDumb: A simple approach that questions our progress in continual test-time adaptation","created":"2023-06-08","cited_by_count":53,"area":null},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52,"area":null},{"id":"2311.17137","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","created":"2023-11-28","cited_by_count":50,"area":"diffusion"},{"id":"2310.15171","title":"RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions","created":"2023-10-23","cited_by_count":49,"area":null},{"id":"2212.09713","title":"A Probabilistic Framework for Lifelong Test-Time Adaptation","created":"2022-12-19","cited_by_count":46,"area":null},{"id":"2306.00987","title":"StyleGAN knows Normal, Depth, Albedo, and More","created":"2023-06-01","cited_by_count":44,"area":null},{"id":"2604.14268","title":"HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds","created":"2026-04-15","cited_by_count":44,"area":"wm"},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41,"area":null},{"id":"2311.18832","title":"Exploiting Diffusion Prior for Generalizable Dense Prediction","created":"2023-11-30","cited_by_count":38,"area":"diffusion"},{"id":"2503.07535","title":"LBM: Latent Bridge Matching for Fast Image-to-Image Translation","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2410.15971","title":"Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly","created":"2024-10-21","cited_by_count":35,"area":null},{"id":"2306.07713","title":"Robustness of SAM: Segment Anything Under Corruptions and Beyond","created":"2023-06-13","cited_by_count":31,"area":null},{"id":"2403.17009","title":"Is Your LiDAR Placement Optimized for 3D Scene Understanding?","created":"2024-03-25","cited_by_count":26,"area":null},{"id":"2404.09833","title":"Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video","created":"2024-04-15","cited_by_count":26,"area":null},{"id":"2504.11427","title":"NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors","created":"2025-04-15","cited_by_count":25,"area":"diffusion"},{"id":"2305.17102","title":"GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation","created":"2023-05-26","cited_by_count":24,"area":null},{"id":"2405.05012","title":"The Entropy Enigma: Success and Failure of Entropy Minimization","created":"2024-05-08","cited_by_count":24,"area":null},{"id":"2310.06347","title":"JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling","created":"2023-10-10","cited_by_count":23,"area":"diffusion"},{"id":"2306.09349","title":"UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video","created":"2023-06-15","cited_by_count":22,"area":null},{"id":"2501.05446","title":"Relative Pose Estimation through Affine Corrections of Monocular Depth Priors","created":"2025-01-09","cited_by_count":18,"area":null},{"id":"2307.03133","title":"Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification","created":"2023-07-06","cited_by_count":17,"area":null},{"id":"2405.21074","title":"Latent Intrinsics Emerge from Training to Relight","created":"2024-05-31","cited_by_count":17,"area":null},{"id":"2505.16441","title":"Ranked Entropy Minimization for Continual Test-Time Adaptation","created":"2025-05-22","cited_by_count":17,"area":null},{"id":"2302.14309","title":"Temporal Coherent Test-Time Optimization for Robust Video Classification","created":"2023-02-28","cited_by_count":15,"area":null},{"id":"2304.04795","title":"Evaluation of Test-Time Adaptation Under Computational Time Constraints","created":"2023-04-10","cited_by_count":15,"area":null},{"id":"2312.05277","title":"3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection","created":"2023-12-08","cited_by_count":15,"area":null},{"id":"2309.10255","title":"RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery","created":"2023-09-19","cited_by_count":14,"area":null},{"id":"2507.01955","title":"How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks","created":"2025-07-02","cited_by_count":14,"area":null},{"id":"2301.04075","title":"Benchmarking Robustness in Neural Radiance Fields","created":"2023-01-10","cited_by_count":13,"area":null},{"id":"2307.15061","title":"The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation","created":"2023-07-27","cited_by_count":13,"area":null},{"id":"2308.15499","title":"Classification robustness to common optical aberrations","created":"2023-08-29","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":"2307.11823","title":"HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness","created":"2023-07-21","cited_by_count":12,"area":null},{"id":"2509.17430","title":"EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device","created":"2025-09-22","cited_by_count":12,"area":null},{"id":"2311.17833","title":"DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations","created":"2023-11-29","cited_by_count":11,"area":null},{"id":"2410.03030","title":"Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2411.17249","title":"Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors","created":"2024-11-26","cited_by_count":11,"area":null},{"id":"2212.11720","title":"GOOD: Exploring Geometric Cues for Detecting Objects in an Open World","created":"2022-12-22","cited_by_count":10,"area":null},{"id":"2303.09152","title":"Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation","created":"2023-03-16","cited_by_count":10,"area":null},{"id":"2309.15762","title":"Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback","created":"2023-09-27","cited_by_count":10,"area":null},{"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":"2301.02184","title":"Chat2Map: Efficient Scene Mapping from Multi-Ego Conversations","created":"2023-01-04","cited_by_count":8,"area":null},{"id":"2301.12993","title":"Benchmarking Robustness to Adversarial Image Obfuscations","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2407.11906","title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2411.17240","title":"Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration","created":"2024-11-26","cited_by_count":8,"area":"diffusion"},{"id":"2505.09368","title":"RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2304.01239","title":"Online Distillation with Continual Learning for Cyclic Domain Shifts","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2308.14899","title":"RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learning","created":"2023-08-28","cited_by_count":6,"area":null},{"id":"2310.04285","title":"Assessing Robustness via Score-Based Adversarial Image Generation","created":"2023-10-06","cited_by_count":6,"area":null},{"id":"2412.20506","title":"DPBridge: Latent Diffusion Bridge for Dense Prediction","created":"2024-12-29","cited_by_count":6,"area":"diffusion"},{"id":"2512.21003","title":"MVInverse: Feed-forward Multi-view Inverse Rendering in Seconds","created":"2025-12-24","cited_by_count":6,"area":null},{"id":"2204.12143","title":"Deeper Insights into the Robustness of ViTs towards Common Corruptions","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2312.11535","title":"High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2410.23142","title":"FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2503.03519","title":"Do ImageNet-trained models learn shortcuts? The impact of frequency shortcuts on generalization","created":"2025-03-05","cited_by_count":5,"area":null},{"id":"2505.04835","title":"Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2510.26800","title":"OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2212.00987","title":"Sparse SPN: Depth Completion from Sparse Keypoints","created":"2022-12-02","cited_by_count":3,"area":null},{"id":"2307.01425","title":"Consistent Multimodal Generation via A Unified GAN Framework","created":"2023-07-04","cited_by_count":3,"area":null},{"id":"2406.02535","title":"Enhancing 2D Representation Learning with a 3D Prior","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2408.09336","title":"Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration","created":"2024-08-18","cited_by_count":3,"area":null},{"id":"2503.06471","title":"Online Dense Point Tracking with Streaming Memory","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2506.14808","title":"PARC: A Quantitative Framework Uncovering the Symmetries within Vision Language Models","created":"2025-06-03","cited_by_count":3,"area":"mllm"},{"id":"2511.12978","title":"Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach","created":"2025-11-17","cited_by_count":3,"area":"mllm"},{"id":"2606.00828","title":"RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes","created":"2026-05-30","cited_by_count":3,"area":"mllm"},{"id":"2206.10858","title":"Robust Universal Adversarial Perturbations","created":"2022-06-22","cited_by_count":2,"area":null},{"id":"2309.07021","title":"Exploiting Multiple Priors for Neural 3D Indoor Reconstruction","created":"2023-09-13","cited_by_count":2,"area":null},{"id":"2402.19401","title":"Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2410.06982","title":"Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation","created":"2024-10-09","cited_by_count":2,"area":"distill"},{"id":"2503.17027","title":"RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2504.18510","title":"Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models","created":"2025-04-25","cited_by_count":2,"area":null},{"id":"2507.17651","title":"CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts","created":"2025-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2602.00839","title":"TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2306.15574","title":"See Through the Fog: Curriculum Learning with Progressive Occlusion in Medical Imaging","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2311.03414","title":"A Generative Neural Network Approach for 3D Multi-Criteria Design Generation and Optimization of an Engine Mount for an Unmanned Air Vehicle","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2311.10523","title":"Removing Adverse Volumetric Effects From Trained Neural Radiance Fields","created":"2023-11-17","cited_by_count":1,"area":null},{"id":"2405.06765","title":"Common Corruptions for Enhancing and Evaluating Robustness in Air-to-Air Visual Object Detection","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2406.00929","title":"Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometry","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2411.11691","title":"Towards Degradation-Robust Reconstruction in Generalizable NeRF","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2412.20034","title":"Maintain Plasticity in Long-timescale Continual Test-time Adaptation","created":"2024-12-28","cited_by_count":1,"area":null},{"id":"2509.02182","title":"ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.02956","title":"Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2605.15906","title":"A Causally Grounded Taxonomy for Image Degradation Robustness Evaluation","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.16258","title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2301.11790","title":"Leveraging the Third Dimension in Contrastive Learning","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2402.13848","title":"Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps","created":"2024-02-21","cited_by_count":0,"area":null}],"next_cursor":"100"}