{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/depth-estimation/papers/11","list_of":"/task/depth-estimation","task":"Depth Estimation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":11,"pages_in_order":25,"rows_per_page":100,"rows":[1001,1100],"of":2454,"counts":{"archive_papers_tagged":2454,"with_a_code_link":1029,"where_syntology_ran_a_sample":292,"not_listed_spam_title":0,"listed":2454,"listed_where_code_ran":292,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":260,"every_run_a_failure_of_syntologys_instrument":32,"listed_with_a_run_with_no_instrument_failure":260,"listed_every_run_a_failure_of_syntologys_instrument":32,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/depth-estimation","prev":"/task/depth-estimation/papers/10","next":"/task/depth-estimation/papers/12","papers":[{"url":"/paper/planenet-piece-wise-planar-reconstruction","slug":"planenet-piece-wise-planar-reconstruction","title":"PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image","date":"2018-04-17","arxiv_id":"1804.06278","repositories_listed":1,"syntology":null},{"url":"/paper/dual-cnn-models-for-unsupervised-monocular","slug":"dual-cnn-models-for-unsupervised-monocular","title":"Dual CNN Models for Unsupervised Monocular Depth Estimation","date":"2018-04-16","arxiv_id":"1804.06324","repositories_listed":1,"syntology":null},{"url":"/paper/structured-attention-guided-convolutional","slug":"structured-attention-guided-convolutional","title":"Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation","date":"2018-03-29","arxiv_id":"1803.11029","repositories_listed":1,"syntology":null},{"url":"/paper/deep-depth-completion-of-a-single-rgb-d-image","slug":"deep-depth-completion-of-a-single-rgb-d-image","title":"Deep Depth Completion of a Single RGB-D Image","date":"2018-03-25","arxiv_id":"1803.09326","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-depth-estimation-3d-face","slug":"unsupervised-depth-estimation-3d-face","title":"Unsupervised Depth Estimation, 3D Face Rotation and Replacement","date":"2018-03-25","arxiv_id":"1803.09202","repositories_listed":1,"syntology":null},{"url":"/paper/deep-component-analysis-via-alternating","slug":"deep-component-analysis-via-alternating","title":"Deep Component Analysis via Alternating Direction Neural Networks","date":"2018-03-16","arxiv_id":"1803.06407","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-learning-of-monocular-depth-1","slug":"unsupervised-learning-of-monocular-depth-1","title":"Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction","date":"2018-03-11","arxiv_id":"1803.03893","repositories_listed":1,"syntology":null},{"url":"/paper/single-view-stereo-matching","slug":"single-view-stereo-matching","title":"Single View Stereo Matching","date":"2018-03-07","arxiv_id":"1803.02612","repositories_listed":1,"syntology":null},{"url":"/paper/monocular-depth-estimation-using-multi-scale","slug":"monocular-depth-estimation-using-multi-scale","title":"Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep Networks","date":"2018-03-01","arxiv_id":"1803.00891","repositories_listed":1,"syntology":null},{"url":"/paper/estimated-depth-map-helps-image","slug":"estimated-depth-map-helps-image","title":"Estimated Depth Map Helps Image Classification","date":"2017-09-20","arxiv_id":"1709.07077","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-discovery-and-geotagging-of-objects","slug":"automatic-discovery-and-geotagging-of-objects","title":"Automatic Discovery and Geotagging of Objects from Street View Imagery","date":"2017-08-28","arxiv_id":"1708.08417","repositories_listed":1,"syntology":null},{"url":"/paper/sparsity-invariant-cnns","slug":"sparsity-invariant-cnns","title":"Sparsity Invariant CNNs","date":"2017-08-22","arxiv_id":"1708.06500","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-synthesize-a-4d-rgbd-light-field","slug":"learning-to-synthesize-a-4d-rgbd-light-field","title":"Learning to Synthesize a 4D RGBD Light Field from a Single Image","date":"2017-08-10","arxiv_id":"1708.03292","repositories_listed":1,"syntology":null},{"url":"/paper/fast-scene-understanding-for-autonomous","slug":"fast-scene-understanding-for-autonomous","title":"Fast Scene Understanding for Autonomous Driving","date":"2017-08-08","arxiv_id":"1708.02550","repositories_listed":1,"syntology":null},{"url":"/paper/monocular-depth-estimation-with-hierarchical","slug":"monocular-depth-estimation-with-hierarchical","title":"Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum Inference","date":"2017-08-02","arxiv_id":"1708.02287","repositories_listed":1,"syntology":null},{"url":"/paper/the-devil-is-in-the-decoder-classification","slug":"the-devil-is-in-the-decoder-classification","title":"The Devil is in the Decoder: Classification, Regression and GANs","date":"2017-07-18","arxiv_id":"1707.05847","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-scene-parsing-with-perspective","slug":"recurrent-scene-parsing-with-perspective","title":"Recurrent Scene Parsing with Perspective Understanding in the Loop","date":"2017-05-20","arxiv_id":"1705.07238","repositories_listed":1,"syntology":null},{"url":"/paper/single-image-depth-estimation-by-dilated-deep","slug":"single-image-depth-estimation-by-dilated-deep","title":"Single image depth estimation by dilated deep residual convolutional neural network and soft-weight-sum inference","date":"2017-04-27","arxiv_id":"1705.00534","repositories_listed":1,"syntology":null},{"url":"/paper/cnn-slam-real-time-dense-monocular-slam-with","slug":"cnn-slam-real-time-dense-monocular-slam-with","title":"CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction","date":"2017-04-11","arxiv_id":"1704.03489","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cnn-slam-real-time-dense-monocular-slam-with#ran","syntology_url":"https://syntology.ai/paper/1704.03489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.03489"}},"official":null}},{"url":"/paper/segan-segmenting-and-generating-the-invisible","slug":"segan-segmenting-and-generating-the-invisible","title":"SeGAN: Segmenting and Generating the Invisible","date":"2017-03-29","arxiv_id":"1703.10239","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-depth-sensing-for-resource-constrained","slug":"sparse-depth-sensing-for-resource-constrained","title":"Sparse Depth Sensing for Resource-Constrained Robots","date":"2017-03-04","arxiv_id":"1703.01398","repositories_listed":1,"syntology":null},{"url":"/paper/scenenet-rgb-d-5m-photorealistic-images-of","slug":"scenenet-rgb-d-5m-photorealistic-images-of","title":"SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth","date":"2016-12-15","arxiv_id":"1612.05079","repositories_listed":1,"syntology":null},{"url":"/paper/cad2rl-real-single-image-flight-without-a","slug":"cad2rl-real-single-image-flight-without-a","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","date":"2016-11-13","arxiv_id":"1611.04201","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-navigate-in-complex-environments","slug":"learning-to-navigate-in-complex-environments","title":"Learning to Navigate in Complex Environments","date":"2016-11-11","arxiv_id":"1611.03673","repositories_listed":1,"syntology":null},{"url":"/paper/two-stage-convolutional-part-heatmap","slug":"two-stage-convolutional-part-heatmap","title":"Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge","date":"2016-09-29","arxiv_id":"1609.09545","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-filter-networks","slug":"dynamic-filter-networks","title":"Dynamic Filter Networks","date":"2016-05-31","arxiv_id":"1605.09673","repositories_listed":1,"syntology":null},{"url":"/paper/unified-depth-prediction-and-intrinsic-image","slug":"unified-depth-prediction-and-intrinsic-image","title":"Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields","date":"2016-03-21","arxiv_id":"1603.06359","repositories_listed":1,"syntology":null},{"url":"/paper/learning-depth-from-single-monocular-images","slug":"learning-depth-from-single-monocular-images","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","date":"2015-02-26","arxiv_id":"1502.07411","repositories_listed":1,"syntology":null},{"url":"/paper/introduction","slug":"introduction","title":"Introduction","date":"2012-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"p-3-scalable-permutation-equivariant-visual","title":"$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning","date":"2025-07-17","arxiv_id":"2507.13347","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-2m-2-scalable-stereo-matching-model-for","title":"$S^2M^2$: Scalable Stereo Matching Model for Reliable Depth Estimation","date":"2025-07-17","arxiv_id":"2507.13229","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-perception-for-autonomous","title":"Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios","date":"2025-07-16","arxiv_id":"2507.12449","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-depth-foundation-model-recent-trends","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation","date":"2025-07-15","arxiv_id":"2507.11540","repositories_listed":0,"syntology":null},{"url":null,"slug":"cameras-as-relative-positional-encoding","title":"Cameras as Relative Positional Encoding","date":"2025-07-14","arxiv_id":"2507.10496","repositories_listed":0,"syntology":null},{"url":null,"slug":"bydeway-boost-your-multimodal-llm-with-depth","title":"ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way","date":"2025-07-11","arxiv_id":"2507.08679","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-appearance-geometric-cues-for-robust","title":"Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation","date":"2025-07-08","arxiv_id":"2507.05948","repositories_listed":0,"syntology":null},{"url":null,"slug":"lighthousegs-indoor-structure-aware-3d","title":"LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures","date":"2025-07-08","arxiv_id":"2507.06109","repositories_listed":0,"syntology":null},{"url":"/paper/from-pixels-to-damage-severity-estimating","slug":"from-pixels-to-damage-severity-estimating","title":"From Pixels to Damage Severity: Estimating Earthquake Impacts Using Semantic Segmentation of Social Media Images","date":"2025-07-03","arxiv_id":"2507.02781","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustereo-robust-zero-shot-stereo-matching","title":"RobuSTereo: Robust Zero-Shot Stereo Matching under Adverse Weather","date":"2025-07-02","arxiv_id":"2507.01653","repositories_listed":0,"syntology":null},{"url":null,"slug":"underwater-monocular-metric-depth-estimation","title":"Underwater Monocular Metric Depth Estimation: Real-World Benchmarks and Synthetic Fine-Tuning","date":"2025-07-02","arxiv_id":"2507.02148","repositories_listed":0,"syntology":null},{"url":null,"slug":"roboscape-physics-informed-embodied-world","title":"RoboScape: Physics-informed Embodied World Model","date":"2025-06-29","arxiv_id":"2506.23135","repositories_listed":0,"syntology":null},{"url":null,"slug":"thermaldiffusion-visual-to-thermal-image-to","title":"ThermalDiffusion: Visual-to-Thermal Image-to-Image Translation for Autonomous Navigation","date":"2025-06-26","arxiv_id":"2506.20969","repositories_listed":0,"syntology":null},{"url":null,"slug":"stereodiff-stereo-diffusion-synergy-for-video","title":"StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation","date":"2025-06-25","arxiv_id":"2506.20756","repositories_listed":0,"syntology":null},{"url":null,"slug":"thirdeye-cue-aware-monocular-depth-estimation","title":"THIRDEYE: Cue-Aware Monocular Depth Estimation via Brain-Inspired Multi-Stage Fusion","date":"2025-06-25","arxiv_id":"2506.20877","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-to-locate-vision-based-multisensory","title":"Look to Locate: Vision-Based Multisensory Navigation with 3-D Digital Maps for GNSS-Challenged Environments","date":"2025-06-24","arxiv_id":"2506.19827","repositories_listed":0,"syntology":null},{"url":null,"slug":"bulletgen-improving-4d-reconstruction-with","title":"BulletGen: Improving 4D Reconstruction with Bullet-Time Generation","date":"2025-06-23","arxiv_id":"2506.18601","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamcube-3d-panorama-generation-via-multi","title":"DreamCube: 3D Panorama Generation via Multi-plane Synchronization","date":"2025-06-20","arxiv_id":"2506.17206","repositories_listed":0,"syntology":null},{"url":null,"slug":"monocular-one-shot-metric-depth-alignment-for","title":"Monocular One-Shot Metric-Depth Alignment for RGB-Based Robot Grasping","date":"2025-06-20","arxiv_id":"2506.17110","repositories_listed":0,"syntology":null},{"url":null,"slug":"racalnet-radar-calibration-network-for-sparse","title":"RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation","date":"2025-06-18","arxiv_id":"2506.15560","repositories_listed":0,"syntology":null},{"url":null,"slug":"difuse-net-rgb-and-dual-pixel-depth","title":"DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning","date":"2025-06-17","arxiv_id":"2506.14709","repositories_listed":0,"syntology":null},{"url":null,"slug":"dcirnet-depth-completion-with-iterative","title":"DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects","date":"2025-06-11","arxiv_id":"2506.09491","repositories_listed":0,"syntology":null},{"url":null,"slug":"egom2p-egocentric-multimodal-multitask","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","date":"2025-06-09","arxiv_id":"2506.07886","repositories_listed":0,"syntology":null},{"url":null,"slug":"flow-anything-learning-real-world-optical","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","date":"2025-06-09","arxiv_id":"2506.07740","repositories_listed":0,"syntology":null},{"url":null,"slug":"hidden-in-plain-sight-vlms-overlook-their","title":"Hidden in plain sight: VLMs overlook their visual representations","date":"2025-06-09","arxiv_id":"2506.08008","repositories_listed":0,"syntology":null},{"url":null,"slug":"jamais-vu-exposing-the-generalization-gap-in","title":"Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence","date":"2025-06-09","arxiv_id":"2506.08220","repositories_listed":0,"syntology":null},{"url":null,"slug":"dark-channel-assisted-depth-from-defocus-from-1","title":"Dark Channel-Assisted Depth-from-Defocus from a Single Image","date":"2025-06-07","arxiv_id":"2506.06643","repositories_listed":0,"syntology":null},{"url":null,"slug":"aerial-multi-view-stereo-via-adaptive-depth","title":"Aerial Multi-View Stereo via Adaptive Depth Range Inference and Normal Cues","date":"2025-06-06","arxiv_id":"2506.05655","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-transforming-a-unified-and-training","title":"Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration","date":"2025-06-06","arxiv_id":"2506.05709","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-aware-radar-camera-depth-estimation","title":"Structure-Aware Radar-Camera Depth Estimation","date":"2025-06-05","arxiv_id":"2506.05008","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-better-ssim-loss-for-unsupervised","title":"Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation","date":"2025-06-05","arxiv_id":"2506.04758","repositories_listed":0,"syntology":null},{"url":null,"slug":"voyager-long-range-and-world-consistent-video","title":"Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation","date":"2025-06-04","arxiv_id":"2506.04225","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-foundation-models-for-robust-and","title":"Harnessing Foundation Models for Robust and Generalizable 6-DOF Bronchoscopy Localization","date":"2025-05-30","arxiv_id":"2505.24249","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-geometric-and-semantic-foundation","title":"Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimation","date":"2025-05-29","arxiv_id":"2505.23400","repositories_listed":0,"syntology":null},{"url":null,"slug":"geoman-temporally-consistent-human-geometry","title":"GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion","date":"2025-05-29","arxiv_id":"2505.23085","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultrafast-high-flux-single-photon-lidar","title":"Ultrafast High-Flux Single-Photon LiDAR Simulator via Neural Mapping","date":"2025-05-29","arxiv_id":"2505.23992","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-robograsp-generalized-robotic","title":"Spatial RoboGrasp: Generalized Robotic Grasping Control Policy","date":"2025-05-27","arxiv_id":"2505.20814","repositories_listed":0,"syntology":null},{"url":null,"slug":"spikestereonet-a-brain-inspired-framework-for","title":"SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams","date":"2025-05-26","arxiv_id":"2505.19487","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-single-images-to-motion-policies-via","title":"From Single Images to Motion Policies via Video-Generation Environment Representations","date":"2025-05-25","arxiv_id":"2505.19306","repositories_listed":0,"syntology":null},{"url":null,"slug":"evidencemoe-a-physics-guided-mixture-of","title":"EvidenceMoE: A Physics-Guided Mixture-of-Experts with Evidential Critics for Advancing Fluorescence Light Detection and Ranging in Scattering Media","date":"2025-05-23","arxiv_id":"2505.21532","repositories_listed":0,"syntology":null},{"url":null,"slug":"baddepth-backdoor-attacks-against-monocular","title":"BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World","date":"2025-05-22","arxiv_id":"2505.16154","repositories_listed":0,"syntology":null},{"url":null,"slug":"radarrgbd-a-multi-sensor-fusion-dataset-for","title":"RadarRGBD A Multi-Sensor Fusion Dataset for Perception with RGB-D and mmWave Radar","date":"2025-05-21","arxiv_id":"2505.15860","repositories_listed":0,"syntology":null},{"url":null,"slug":"m3depth-wavelet-enhanced-depth-estimation-on","title":"M3Depth: Wavelet-Enhanced Depth Estimation on Mars via Mutual Boosting of Dual-Modal Data","date":"2025-05-20","arxiv_id":"2505.14159","repositories_listed":0,"syntology":null},{"url":null,"slug":"db3d-l-depth-aware-bev-feature-transformation","title":"DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection","date":"2025-05-19","arxiv_id":"2505.13266","repositories_listed":0,"syntology":null},{"url":null,"slug":"ia-mvs-instance-focused-adaptive-depth","title":"IA-MVS: Instance-Focused Adaptive Depth Sampling for Multi-View Stereo","date":"2025-05-19","arxiv_id":"2505.12714","repositories_listed":0,"syntology":null},{"url":null,"slug":"monomobility-zero-shot-3d-mobility-analysis","title":"MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos","date":"2025-05-17","arxiv_id":"2505.11868","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11439","title":"SurgPose: Generalisable Surgical Instrument Pose Estimation using Zero-Shot Learning and Stereo Vision","date":"2025-05-16","arxiv_id":"2505.11439","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-anything-with-any-prior","title":"Depth Anything with Any Prior","date":"2025-05-15","arxiv_id":"2505.10565","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointdistill-adaptive-multi-task-distillation","title":"JointDistill: Adaptive Multi-Task Distillation for Joint Depth Estimation and Scene Segmentation","date":"2025-05-15","arxiv_id":"2505.10057","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-zero-shot-stereo-matching-using","title":"Boosting Zero-shot Stereo Matching using Large-scale Mixed Images Sources in the Real World","date":"2025-05-13","arxiv_id":"2505.08607","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-monocular-vision","title":"Reinforcement Learning-Based Monocular Vision Approach for Autonomous UAV Landing","date":"2025-05-11","arxiv_id":"2505.06963","repositories_listed":0,"syntology":null},{"url":null,"slug":"electricsight-3d-hazard-monitoring-for-power","title":"ElectricSight: 3D Hazard Monitoring for Power Lines Using Low-Cost Sensors","date":"2025-05-10","arxiv_id":"2505.06573","repositories_listed":0,"syntology":null},{"url":null,"slug":"camera-only-bird-s-eye-view-perception-a","title":"Camera-Only Bird's Eye View Perception: A Neural Approach to LiDAR-Free Environmental Mapping for Autonomous Vehicles","date":"2025-05-09","arxiv_id":"2505.06113","repositories_listed":0,"syntology":null},{"url":null,"slug":"monocop-chain-of-prediction-for-monocular-3d","title":"MonoCoP: Chain-of-Prediction for Monocular 3D Object Detection","date":"2025-05-07","arxiv_id":"2505.04594","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-for-robotic-leaf","title":"Self-Supervised Learning for Robotic Leaf Manipulation: A Hybrid Geometric-Neural Approach","date":"2025-05-06","arxiv_id":"2505.03702","repositories_listed":0,"syntology":null},{"url":null,"slug":"delta-dense-depth-from-events-and-lidar-using","title":"DELTA: Dense Depth from Events and LiDAR using Transformer's Attention","date":"2025-05-05","arxiv_id":"2505.02593","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-situ-and-non-contact-etch-depth-prediction","title":"In-situ and Non-contact Etch Depth Prediction in Plasma Etching via Machine Learning (ANN & BNN) and Digital Image Colorimetry","date":"2025-05-03","arxiv_id":"2505.03826","repositories_listed":0,"syntology":null},{"url":null,"slug":"posepilot-steering-camera-pose-for-generative","title":"PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth","date":"2025-05-03","arxiv_id":"2505.01729","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmdepth-lightweight-mamba-based-monocular","title":"LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment","date":"2025-05-02","arxiv_id":"2505.00980","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointdit-enhancing-rgb-depth-joint-modeling","title":"JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers","date":"2025-05-01","arxiv_id":"2505.00482","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-geometry-supervision-for-underwater","title":"Dense Geometry Supervision for Underwater Depth Estimation","date":"2025-04-25","arxiv_id":"2504.18233","repositories_listed":0,"syntology":null},{"url":null,"slug":"occlusion-aware-self-supervised-monocular","title":"Occlusion-Aware Self-Supervised Monocular Depth Estimation for Weak-Texture Endoscopic Images","date":"2025-04-24","arxiv_id":"2504.17582","repositories_listed":0,"syntology":null},{"url":null,"slug":"derd-net-learning-depth-from-event-based-ray","title":"DERD-Net: Learning Depth from Event-based Ray Densities","date":"2025-04-22","arxiv_id":"2504.15863","repositories_listed":0,"syntology":null},{"url":null,"slug":"univg-a-generalist-diffusion-model-for","title":"UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing","date":"2025-04-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vistadepth-frequency-modulation-with-bias","title":"VistaDepth: Frequency Modulation With Bias Reweighting For Enhanced Long-Range Depth Estimation","date":"2025-04-21","arxiv_id":"2504.15095","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-pothole-detection-and","title":"Enhancing Pothole Detection and Characterization: Integrated Segmentation and Depth Estimation in Road Anomaly Systems","date":"2025-04-18","arxiv_id":"2504.13648","repositories_listed":0,"syntology":null},{"url":null,"slug":"occlusion-ordered-semantic-instance","title":"Occlusion-Ordered Semantic Instance Segmentation","date":"2025-04-18","arxiv_id":"2504.14054","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-operating-room-workflow","title":"Privacy-Preserving Operating Room Workflow Analysis using Digital Twins","date":"2025-04-17","arxiv_id":"2504.12552","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsgs-improving-gaussian-splatting-for","title":"TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors","date":"2025-04-17","arxiv_id":"2504.12799","repositories_listed":0,"syntology":null},{"url":null,"slug":"metric-solver-sliding-anchored-metric-depth","title":"Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image","date":"2025-04-16","arxiv_id":"2504.12103","repositories_listed":0,"syntology":null},{"url":null,"slug":"tacodepth-towards-efficient-radar-camera","title":"TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion","date":"2025-04-16","arxiv_id":"2504.11773","repositories_listed":0,"syntology":null}],"record_sha256":"3ce01b75ef2c666efa06f8368851dfa3b3c2aef8b5529f8bdd68eb42e06da022","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}