{"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/13","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":13,"pages_in_order":25,"rows_per_page":100,"rows":[1201,1300],"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/12","next":"/task/depth-estimation/papers/14","papers":[{"url":null,"slug":"fpga-based-acceleration-of-neural-network-for","title":"FPGA-based Acceleration of Neural Network for Image Classification using Vitis AI","date":"2024-12-30","arxiv_id":"2412.20974","repositories_listed":0,"syntology":null},{"url":null,"slug":"dpbridge-latent-diffusion-bridge-for-dense","title":"DPBridge: Latent Diffusion Bridge for Dense Prediction","date":"2024-12-29","arxiv_id":"2412.20506","repositories_listed":0,"syntology":null},{"url":null,"slug":"metricdepth-enhancing-monocular-depth","title":"MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learning","date":"2024-12-29","arxiv_id":"2412.20390","repositories_listed":0,"syntology":null},{"url":null,"slug":"depthmamba-with-adaptive-fusion","title":"DepthMamba with Adaptive Fusion","date":"2024-12-28","arxiv_id":"2412.19964","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modality-driven-lora-for-adverse","title":"Multi-Modality Driven LoRA for Adverse Condition Depth Estimation","date":"2024-12-28","arxiv_id":"2412.20162","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-depth-based-pipeline-for-selfie","title":"An End-to-End Depth-Based Pipeline for Selfie Image Rectification","date":"2024-12-26","arxiv_id":"2412.19189","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-monocular-depth-from-events-via","title":"Learning Monocular Depth from Events via Egomotion Compensation","date":"2024-12-26","arxiv_id":"2412.19067","repositories_listed":0,"syntology":null},{"url":null,"slug":"mvs-gs-high-quality-3d-gaussian-splatting","title":"MVS-GS: High-Quality 3D Gaussian Splatting Mapping via Online Multi-View Stereo","date":"2024-12-26","arxiv_id":"2412.19130","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-monocular-3d-object-detection-from","title":"Revisiting Monocular 3D Object Detection from Scene-Level Depth Retargeting to Instance-Level Spatial Refinement","date":"2024-12-26","arxiv_id":"2412.19165","repositories_listed":0,"syntology":null},{"url":null,"slug":"rsgaussian-3d-gaussian-splatting-with-lidar","title":"RSGaussian:3D Gaussian Splatting with LiDAR for Aerial Remote Sensing Novel View Synthesis","date":"2024-12-24","arxiv_id":"2412.18380","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowing-from-words-to-pixels-a-framework-for","title":"Flowing from Words to Pixels: A Framework for Cross-Modality Evolution","date":"2024-12-19","arxiv_id":"2412.15213","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-4d-representations","title":"Scaling 4D Representations","date":"2024-12-19","arxiv_id":"2412.15212","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundation-models-meet-low-cost-sensors-test","title":"Foundation Models Meet Low-Cost Sensors: Test-Time Adaptation for Rescaling Disparity for Zero-Shot Metric Depth Estimation","date":"2024-12-18","arxiv_id":"2412.14103","repositories_listed":0,"syntology":null},{"url":null,"slug":"marigold-dc-zero-shot-monocular-depth","title":"Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion","date":"2024-12-18","arxiv_id":"2412.13389","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptdet-a-lightweight-3d-object-detection","title":"PromptDet: A Lightweight 3D Object Detection Framework with LiDAR Prompts","date":"2024-12-17","arxiv_id":"2412.12460","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-centric-dehazing-and-depth-estimation","title":"Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video","date":"2024-12-16","arxiv_id":"2412.11395","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-mind-building-versatile-monocular-indoor-3d","title":"V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations","date":"2024-12-16","arxiv_id":"2412.11412","repositories_listed":0,"syntology":null},{"url":null,"slug":"mal-cluster-masked-and-multi-task-pretraining","title":"MAL: Cluster-Masked and Multi-Task Pretraining for Enhanced xLSTM Vision Performance","date":"2024-12-14","arxiv_id":"2412.10730","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-view-completion-models-are-zero-shot","title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","date":"2024-12-12","arxiv_id":"2412.09072","repositories_listed":0,"syntology":null},{"url":null,"slug":"stereo4d-learning-how-things-move-in-3d-from","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","date":"2024-12-12","arxiv_id":"2412.09621","repositories_listed":0,"syntology":null},{"url":null,"slug":"t-svg-text-driven-stereoscopic-video","title":"T-SVG: Text-Driven Stereoscopic Video Generation","date":"2024-12-12","arxiv_id":"2412.09323","repositories_listed":0,"syntology":null},{"url":null,"slug":"blade-single-view-body-mesh-learning-through","title":"BLADE: Single-view Body Mesh Learning through Accurate Depth Estimation","date":"2024-12-11","arxiv_id":"2412.08640","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-depth-from-event-focal-stack","title":"Dense Depth from Event Focal Stack","date":"2024-12-11","arxiv_id":"2412.08120","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-shared-and-task-specific","title":"Balancing Shared and Task-Specific Representations: A Hybrid Approach to Depth-Aware Video Panoptic Segmentation","date":"2024-12-10","arxiv_id":"2412.07966","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-fields-capturing-light-fields-at-high","title":"Event fields: Capturing light fields at high speed, resolution, and dynamic range","date":"2024-12-09","arxiv_id":"2412.06191","repositories_listed":0,"syntology":null},{"url":null,"slug":"omni-scene-omni-gaussian-representation-for","title":"Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction","date":"2024-12-09","arxiv_id":"2412.06273","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-device-self-supervised-learning-of-low","title":"On-Device Self-Supervised Learning of Low-Latency Monocular Depth from Only Events","date":"2024-12-09","arxiv_id":"2412.06359","repositories_listed":0,"syntology":null},{"url":null,"slug":"sphereuformer-a-u-shaped-transformer-for","title":"SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception","date":"2024-12-09","arxiv_id":"2412.06968","repositories_listed":0,"syntology":null},{"url":null,"slug":"gvdepth-zero-shot-monocular-depth-estimation","title":"GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion","date":"2024-12-08","arxiv_id":"2412.06080","repositories_listed":0,"syntology":null},{"url":null,"slug":"simc3d-a-simple-contrastive-3d-pretraining","title":"SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB Images","date":"2024-12-06","arxiv_id":"2412.05274","repositories_listed":0,"syntology":null},{"url":null,"slug":"dualpm-dual-posed-canonical-point-maps-for-3d","title":"DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction","date":"2024-12-05","arxiv_id":"2412.04464","repositories_listed":0,"syntology":null},{"url":null,"slug":"laa-net-a-physical-prior-knowledge-based","title":"LAA-Net: A Physical-prior-knowledge Based Network for Robust Nighttime Depth Estimation","date":"2024-12-05","arxiv_id":"2412.04666","repositories_listed":0,"syntology":null},{"url":null,"slug":"mt3dnet-multi-task-learning-network-for-3d","title":"MT3DNet: Multi-Task learning Network for 3D Surgical Scene Reconstruction","date":"2024-12-05","arxiv_id":"2412.03928","repositories_listed":0,"syntology":null},{"url":null,"slug":"align3r-aligned-monocular-depth-estimation","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","date":"2024-12-04","arxiv_id":"2412.03079","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-scene-reconstruction-from-light-field","title":"Dense Scene Reconstruction from Light-Field Images Affected by Rolling Shutter","date":"2024-12-04","arxiv_id":"2412.03518","repositories_listed":0,"syntology":null},{"url":null,"slug":"multigo-towards-multi-level-geometry-learning","title":"MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction","date":"2024-12-04","arxiv_id":"2412.03103","repositories_listed":0,"syntology":null},{"url":null,"slug":"perception-tokens-enhance-visual-reasoning-in","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","date":"2024-12-04","arxiv_id":"2412.03548","repositories_listed":0,"syntology":null},{"url":null,"slug":"amodal-depth-anything-amodal-depth-estimation","title":"Amodal Depth Anything: Amodal Depth Estimation in the Wild","date":"2024-12-03","arxiv_id":"2412.02336","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-exposure-stereo-for-extended-dynamic","title":"Dual Exposure Stereo for Extended Dynamic Range 3D Imaging","date":"2024-12-03","arxiv_id":"2412.02351","repositories_listed":0,"syntology":null},{"url":null,"slug":"gsgtrack-gaussian-splatting-guided-object","title":"GSGTrack: Gaussian Splatting-Guided Object Pose Tracking from RGB Videos","date":"2024-12-03","arxiv_id":"2412.02267","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-shot-metric-depth-from-focused","title":"Single-Shot Metric Depth from Focused Plenoptic Cameras","date":"2024-12-03","arxiv_id":"2412.02386","repositories_listed":0,"syntology":null},{"url":null,"slug":"avs-net-audio-visual-scale-net-for-self","title":"AVS-Net: Audio-Visual Scale Net for Self-supervised Monocular Metric Depth Estimation","date":"2024-12-02","arxiv_id":"2412.01637","repositories_listed":0,"syntology":null},{"url":null,"slug":"holodrive-holistic-2d-3d-multi-modal-street","title":"HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving","date":"2024-12-02","arxiv_id":"2412.01407","repositories_listed":0,"syntology":null},{"url":null,"slug":"static-surface-temporal-affine-for-time","title":"STATIC : Surface Temporal Affine for TIme Consistency in Video Monocular Depth Estimation","date":"2024-12-02","arxiv_id":"2412.01090","repositories_listed":0,"syntology":null},{"url":null,"slug":"fiffdepth-feed-forward-transformation-of","title":"FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation","date":"2024-12-01","arxiv_id":"2412.00671","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussian-splashing-direct-volumetric","title":"Gaussian Splashing: Direct Volumetric Rendering Underwater","date":"2024-11-29","arxiv_id":"2411.19588","repositories_listed":0,"syntology":null},{"url":null,"slug":"monopp-metric-scaled-self-supervised","title":"MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications","date":"2024-11-29","arxiv_id":"2411.19717","repositories_listed":0,"syntology":null},{"url":"/paper/sparc-sparse-radar-camera-fusion-for-3d","slug":"sparc-sparse-radar-camera-fusion-for-3d","title":"SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection","date":"2024-11-29","arxiv_id":"2411.19860","repositories_listed":0,"syntology":null},{"url":null,"slug":"360recon-an-accurate-reconstruction-method","title":"360Recon: An Accurate Reconstruction Method Based on Depth Fusion from 360 Images","date":"2024-11-28","arxiv_id":"2411.19102","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-depth-without-video-models","title":"Video Depth without Video Models","date":"2024-11-28","arxiv_id":"2411.19189","repositories_listed":0,"syntology":null},{"url":null,"slug":"sharpdepth-sharpening-metric-depth","title":"SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation","date":"2024-11-27","arxiv_id":"2411.18229","repositories_listed":0,"syntology":null},{"url":null,"slug":"depthcues-evaluating-monocular-depth","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","date":"2024-11-26","arxiv_id":"2411.17385","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-adaptation-based-all-weather-removal","title":"Low-rank Adaptation-based All-Weather Removal for Autonomous Navigation","date":"2024-11-26","arxiv_id":"2411.17814","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatially-visual-perception-for-end-to-end","title":"Spatially Visual Perception for End-to-End Robotic Learning","date":"2024-11-26","arxiv_id":"2411.17458","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-omnimatte-learning-to-decompose","title":"Generative Omnimatte: Learning to Decompose Video into Layers","date":"2024-11-25","arxiv_id":"2411.16683","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussian-scenes-pose-free-sparse-view-scene","title":"Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors","date":"2024-11-24","arxiv_id":"2411.15966","repositories_listed":0,"syntology":null},{"url":null,"slug":"priordiffusion-leverage-language-prior-in","title":"PriorDiffusion: Leverage Language Prior in Diffusion Models for Monocular Depth Estimation","date":"2024-11-24","arxiv_id":"2411.16750","repositories_listed":0,"syntology":null},{"url":null,"slug":"datap-sfm-dynamic-aware-tracking-any-point","title":"DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild","date":"2024-11-20","arxiv_id":"2411.13291","repositories_listed":0,"syntology":null},{"url":null,"slug":"gps-gaussian-generalizable-pixel-wise-3d-1","title":"GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views","date":"2024-11-18","arxiv_id":"2411.11363","repositories_listed":0,"syntology":null},{"url":null,"slug":"mgnicenet-unified-monocular-geometric-scene","title":"MGNiceNet: Unified Monocular Geometric Scene Understanding","date":"2024-11-18","arxiv_id":"2411.11466","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-autoregressive-monocular-depth","title":"Scalable Autoregressive Monocular Depth Estimation","date":"2024-11-18","arxiv_id":"2411.11361","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-aduulm-360-dataset-a-multi-modal-dataset","title":"The ADUULM-360 Dataset -- A Multi-Modal Dataset for Depth Estimation in Adverse Weather","date":"2024-11-18","arxiv_id":"2411.11455","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-using-differentiable","title":"RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering","date":"2024-11-14","arxiv_id":"2411.09749","repositories_listed":0,"syntology":null},{"url":null,"slug":"architect-generating-vivid-and-interactive-3d","title":"Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting","date":"2024-11-14","arxiv_id":"2411.09823","repositories_listed":0,"syntology":null},{"url":null,"slug":"mono2stereo-monocular-knowledge-transfer-for","title":"Mono2Stereo: Monocular Knowledge Transfer for Enhanced Stereo Matching","date":"2024-11-14","arxiv_id":"2411.09151","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-properties-of-diffusion-models-for","title":"Scaling Properties of Diffusion Models for Perceptual Tasks","date":"2024-11-12","arxiv_id":"2411.08034","repositories_listed":0,"syntology":null},{"url":null,"slug":"se-3-equivariant-ray-embeddings-for-implicit","title":"$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation","date":"2024-11-11","arxiv_id":"2411.07326","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplebev-improved-lidar-camera-fusion","title":"SimpleBEV: Improved LiDAR-Camera Fusion Architecture for 3D Object Detection","date":"2024-11-08","arxiv_id":"2411.05292","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-3-epth-self-supervised-depth-estimation","title":"D$^3$epth: Self-Supervised Depth Estimation with Dynamic Mask in Dynamic Scenes","date":"2024-11-07","arxiv_id":"2411.04826","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-bronchoscopy-depth-estimation","title":"Enhancing Bronchoscopy Depth Estimation through Synthetic-to-Real Domain Adaptation","date":"2024-11-07","arxiv_id":"2411.04404","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-stereo-depth-estimation-with-multi","title":"Adaptive Stereo Depth Estimation with Multi-Spectral Images Across All Lighting Conditions","date":"2024-11-06","arxiv_id":"2411.03638","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-disparity-from-dual-pixel-images","title":"Revisiting Disparity from Dual-Pixel Images: Physics-Informed Lightweight Depth Estimation","date":"2024-11-06","arxiv_id":"2411.04714","repositories_listed":0,"syntology":null},{"url":null,"slug":"fewviewgs-gaussian-splatting-with-few-view","title":"FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training","date":"2024-11-04","arxiv_id":"2411.02229","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-domain-generalization-in-self","title":"Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Training","date":"2024-11-04","arxiv_id":"2411.02149","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmpnet-pixel-movement-prediction-network-for","title":"PMPNet: Pixel Movement Prediction Network for Monocular Depth Estimation in Dynamic Scenes","date":"2024-11-04","arxiv_id":"2411.04227","repositories_listed":0,"syntology":null},{"url":null,"slug":"multidepth-multi-sample-priors-for-refining","title":"MultiDepth: Multi-Sample Priors for Refining Monocular Metric Depth Estimations in Indoor Scenes","date":"2024-11-01","arxiv_id":"2411.01048","repositories_listed":0,"syntology":null},{"url":null,"slug":"optical-lens-attack-on-monocular-depth","title":"Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving","date":"2024-10-31","arxiv_id":"2411.00192","repositories_listed":0,"syntology":null},{"url":null,"slug":"nested-resnet-a-vision-based-method-for","title":"Nested ResNet: A Vision-Based Method for Detecting the Sensing Area of a Drop-in Gamma Probe","date":"2024-10-30","arxiv_id":"2410.23154","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-event-alignment-for-monocular-distance","title":"Active Event Alignment for Monocular Distance Estimation","date":"2024-10-29","arxiv_id":"2410.22280","repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-aware-prior-assisted-joint","title":"Segmentation-aware Prior Assisted Joint Global Information Aggregated 3D Building Reconstruction","date":"2024-10-24","arxiv_id":"2410.18433","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-snow-depth-distribution-by","title":"Retrieving snow depth distribution by downscaling ERA5 Reanalysis with ICESat-2 laser altimetry","date":"2024-10-23","arxiv_id":"2410.17934","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncle-unsupervised-continual-learning-of","title":"UnCLe: Unsupervised Continual Learning of Depth Completion","date":"2024-10-23","arxiv_id":"2410.18074","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolo11-and-vision-transformers-based-3d-pose","title":"YOLO11 and Vision Transformers based 3D Pose Estimation of Immature Green Fruits in Commercial Apple Orchards for Robotic Thinning","date":"2024-10-21","arxiv_id":"2410.19846","repositories_listed":0,"syntology":null},{"url":null,"slug":"dh-vton-deep-text-driven-virtual-try-on-via","title":"DH-VTON: Deep Text-Driven Virtual Try-On via Hybrid Attention Learning","date":"2024-10-16","arxiv_id":"2410.12501","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-different-disparity-estimation","title":"Analysis of different disparity estimation techniques on aerial stereo image datasets","date":"2024-10-09","arxiv_id":"2410.06711","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-centric-robust-monocular-depth","title":"Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation","date":"2024-10-09","arxiv_id":"2410.06982","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgical-depth-anything-depth-estimation-for","title":"Surgical Depth Anything: Depth Estimation for Surgical Scenes using Foundation Models","date":"2024-10-09","arxiv_id":"2410.07434","repositories_listed":0,"syntology":null},{"url":null,"slug":"cube360-learning-cubic-field-representation","title":"CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Reality","date":"2024-10-08","arxiv_id":"2410.05735","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-transformer-based-random-walk-for","title":"Vision Transformer based Random Walk for Group Re-Identification","date":"2024-10-08","arxiv_id":"2410.05808","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-nerf-stereo-vision-pioneering-depth","title":"EndoPerfect: High-Accuracy Monocular Depth Estimation and 3D Reconstruction for Endoscopic Surgery via NeRF-Stereo Fusion","date":"2024-10-05","arxiv_id":"2410.04041","repositories_listed":0,"syntology":null},{"url":null,"slug":"drone-stereo-vision-for-radiata-pine-branch-1","title":"Drone Stereo Vision for Radiata Pine Branch Detection and Distance Measurement: Utilizing Deep Learning and YOLO Integration","date":"2024-10-01","arxiv_id":"2410.00503","repositories_listed":0,"syntology":null},{"url":null,"slug":"seamless-augmented-reality-integration-in","title":"Seamless Augmented Reality Integration in Arthroscopy: A Pipeline for Articular Reconstruction and Guidance","date":"2024-10-01","arxiv_id":"2410.00386","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-full-parameter-and-parameter","title":"Towards Full-parameter and Parameter-efficient Self-learning For Endoscopic Camera Depth Estimation","date":"2024-10-01","arxiv_id":"2410.00979","repositories_listed":0,"syntology":null},{"url":null,"slug":"ccdepth-a-lightweight-self-supervised-depth","title":"CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability","date":"2024-09-30","arxiv_id":"2409.19933","repositories_listed":0,"syntology":null},{"url":null,"slug":"fcop-focal-length-estimation-from-category","title":"fCOP: Focal Length Estimation from Category-level Object Priors","date":"2024-09-29","arxiv_id":"2409.19641","repositories_listed":0,"syntology":null},{"url":null,"slug":"kinedepth-utilizing-robot-kinematics-for","title":"KineDepth: Utilizing Robot Kinematics for Online Metric Depth Estimation","date":"2024-09-29","arxiv_id":"2409.19490","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-dataset-for-monocular-depth-estimation","title":"ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts","date":"2024-09-26","arxiv_id":"2409.17851","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-monocular-depth-estimation-6","title":"Self-supervised Monocular Depth Estimation with Large Kernel Attention","date":"2024-09-26","arxiv_id":"2409.17895","repositories_listed":0,"syntology":null},{"url":null,"slug":"eventhdr-from-event-to-high-speed-hdr-videos","title":"EventHDR: from Event to High-Speed HDR Videos and Beyond","date":"2024-09-25","arxiv_id":"2409.17029","repositories_listed":0,"syntology":null},{"url":null,"slug":"optical-lens-attack-on-deep-learning-based","title":"Optical Lens Attack on Deep Learning Based Monocular Depth Estimation","date":"2024-09-25","arxiv_id":"2409.17376","repositories_listed":0,"syntology":null}],"record_sha256":"2805aa52a043c5fe288ac488d4fd8eedb80d41ec252dc200e1e95de5ecda3342","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}