Pos	Paper	Citations	Year
1	Brief: Binary robust independent elementary features	6071	2010
2	EPnP: An Accurate O(n) Solution to the PnP Problem	4492	2009
3	Daisy: An efficient dense descriptor applied to wide-baseline stereo	1982	2009
4	Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes	1946	2012
5	Lift: Learned invariant feature transform	1856	2016
6	Bb8: A scalable, accurate, robust to partial occlusion method for predicting the 3d poses of challenging objects without using depth	1126	2017
7	BRIEF: Computing a local binary descriptor very fast	1097	2011
8	Keypoint recognition using randomized trees	1087	2006
9	Monocular model-based 3D tracking of rigid objects	1082	2005
10	Fast keypoint recognition using random ferns	984	2009
11	Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes	934	2011
12	Sugar: Surface-aligned gaussian splatting for efficient 3d mesh reconstruction and high-quality mesh rendering	901	2024
13	Gradient response maps for real-time detection of textureless objects	832	2011
14	Learning to find good correspondences	769	2018
15	A fast local descriptor for dense matching	719	2008
16	Fast keypoint recognition in ten lines of code	690	2007
17	Randomized trees for real-time keypoint recognition	676	2005
18	Honnotate: A method for 3d annotation of hand and object poses	637	2020
19	Learning descriptors for object recognition and 3d pose estimation	592	2015
20	Stable real-time 3d tracking using online and offline information	567	2004
21	Few-shot object detection and viewpoint estimation for objects in the wild	534	2022
22	Hands deep in deep learning for hand pose estimation	503	2015
23	Tilde: A temporally invariant learned detector	474	2015
24	Combining edge and texture information for real-time accurate 3d camera tracking	462	2004
25	Accurate Non-Iterative 𝑂 (𝑛) Solution to the P𝑛P Problem	457	2007
26	Learning separable filters	424	2013
27	Back to the feature: Learning robust camera localization from pixels to pose	419	2021
28	On pre-trained image features and synthetic images for deep learning	365	2018
29	Pose estimation for category specific multiview object localization	364	2009
30	View-based maps	360	2010
31	Deepprior++: Improving fast and accurate 3d hand pose estimation	352	2017
32	Detecting flying objects using a single moving camera	351	2016
33	Structured prediction of 3d human pose with deep neural networks	344	2016
34	Training a feedback loop for hand pose estimation	341	2015
35	Dominant orientation templates for real-time detection of texture-less objects	327	2010
36	Making deep heatmaps robust to partial occlusions for 3d object pose estimation	307	2018
37	Direct prediction of 3d body poses from motion compensated sequences	285	2016
38	Are sparse representations really relevant for image classification?	276	2011
39	Boosting binary keypoint descriptors	256	2013
40	Going further with point pair features	254	2016
41	Back to mlp: A simple baseline for human motion prediction	252	2023
42	Fast non-rigid surface detection, registration and realistic augmentation	238	2008
43	Keypoint transformer: Solving joint identification in challenging hands and object interactions for accurate 3d pose estimation	238	2022
44	Point matching as a classification problem for fast and robust object pose estimation	235	2004
45	AssemblyNet: A large ensemble of CNNs for 3D whole brain MRI segmentation	234	2020
46	Robust 3D object tracking from monocular images using stable parts	230	2017
47	Multiple 3d object tracking for augmented reality	224	2008
48	Fully automated and stable registration for augmented reality applications	211	2003
49	Flying objects detection from a single moving camera	210	2015
50	Supervised feature learning for curvilinear structure segmentation	209	2013
51	On rendering synthetic images for training an object detector	194	2015
52	3d pose estimation and 3d model retrieval for objects in the wild	180	2018
53	Instant outdoor localization and slam initialization from 2.5 d maps	173	2015
54	Feature mapping for learning fast and accurate 3d pose inference from synthetic images	171	2018
55	You should use regression to detect cells	167	2015
56	Sharpnet: Fast and accurate recovery of occluding contours in monocular depth estimation	161	2019
57	Efficient discriminative projections for compact binary descriptors	160	2012
58	Multiscale centerline detection	160	2015
59	Multiscale centerline detection by learning a scale-space distance transform	156	2014
60	Speed invariant time surface for learning to detect corner points with event-based cameras	155	2019
61	Learning to assign orientations to feature points	151	2016
62	Learning image descriptors with boosting	149	2014
63	Real-time nonrigid surface detection	148	2005
64	Efficient physics-based implementation for realistic hand-object interaction in virtual reality	147	2018
65	Gigapose: Fast and robust novel object pose estimation via one correspondence	142	2024
66	A fully automated approach to segmentation of irregularly shaped cellular structures in EM images	138	2010
67	Templates for 3d object pose estimation revisited: Generalization to new objects and robustness to occlusions	138	2022
68	Closed-form solution to non-rigid 3D surface registration	134	2008
69	Feature harvesting for tracking-by-detection	132	2006
70	Learning image descriptors with the boosting-trick	131	2012
71	Pose estimation and model retrieval for objects in images	126	2020
72	Human body pose detection using Bayesian spatio-temporal templates	123	2006
73	Pose priors for simultaneously solving alignment and correspondence	123	2008
74	Cnos: A strong baseline for cad-based novel object segmentation	122	2023
75	A semi-automatic method for resolving occlusion in augmented reality	120	2000
76	Efficiently creating 3d training data for fine hand pose estimation	118	2016
77	Bop challenge 2023 on detection segmentation and pose estimation of seen and unseen rigid objects	111	2024
78	Learning real-time perspective patch rectification	110	2011
79	Single image depth prediction with wavelet decomposition	110	2021
80	Fusing online and offline information for stable 3d tracking in real-time	108	2003
81	Deep learning: basics and convolutional neural networks (CNNs)	102	2023
82	Keypoint signatures for fast learning and recognition	99	2008
83	Generalized feedback loop for joint hand-object pose estimation	96	2019
84	Predicting sharp and accurate occlusion boundaries in monocular depth estimation using displacement fields	90	2020
85	Fast ray features for learning irregular shapes	88	2009
86	Learning latent representations of 3d human pose with deep neural networks	88	2018
87	Robust 3D tracking with descriptor fields	87	2014
88	Compact signatures for high-speed interest point description and matching	85	2009
89	Zero-baseline 3d map initialization	85	2015
90	Vision-based unmanned aerial vehicle detection and tracking for sense and avoid systems	83	2016
91	Pose determination with semantic segmentation	80	2020
92	Learning lightprobes for mixed reality illumination	77	2017
93	ESM-Blur: Handling & rendering blur in 3D tracking and augmentation	76	2009
94	The haunted book	75	2008
95	Sparse-to-dense hypercolumn matching for long-term visual localization	73	2019
96	Handling occlusion in augmented reality systems: a semi-automatic method	71	2000
97	On object symmetries and 6d pose estimation from images	71	2019
98	Augmented reality for board games	70	2010
99	Towards recognizing feature points using classification trees	70	2010
100	EPnP: Efficient perspective-n-point camera pose estimation	69	2009
101	Geometry-aware network for non-rigid shape prediction from a single view	69	2018
102	Measuring generalisation to unseen viewpoints, articulations, shapes and objects for 3D hand pose estimation under hand-object interaction	66	2020
103	Methods and systems of performing object pose estimation	65	2019
104	Texture-less object tracking with online training using an RGB-D camera	65	2011
105	Accurate and efficient linear structure segmentation by leveraging ad hoc features with learned filters	64	2012
106	An efficient minimal solution for multi-camera motion	63	2015
107	Capturing 3D stretchable surfaces from single images in closed form	63	2009
108	General constraints for batch multiple-target tracking applied to large-scale videomicroscopy	62	2008
109	Online learning of patch perspective rectification for efficient object detection	62	2008
110	Bridging the gap between detection and tracking for 3D monocular video-based motion capture	61	2007
111	Domain transfer for 3d pose estimation from color images without manual annotations	61	2018
112	Method, System and Device for Direct Prediction of 3D Body Poses from Motion Compensated Sequence	60	2017
113	Hashmod: A hashing method for scalable 3D object detection	59	2016
114	Keyframe-based modeling and tracking of multiple 3D objects	59	2010
115	Scalable real-time planar targets tracking for digilog books	59	2010
116	Lu-net: An efficient network for 3d lidar point cloud semantic segmentation based on end-to-end-learned 3d features and u-net	58	2019
117	Combining geometric and appearance priors for robust homography estimation	56	2010
118	Deformable surface tracking ambiguities	55	2007
119	Automated age estimation from hand MRI volumes using deep learning	54	2016
120	Montefloor: Extending mcts for reconstructing accurate large-scale floor plans	54	2021
121	S2DNet: Learning image features for accurate sparse-to-dense matching	54	2020
122	Computer vision–ECCV 2010	50	2010
123	Model Based Augmentation and Testing of an Annotated Hand Pose Dataset, ResearchGate	50	2024
124	Nope: Novel object pose estimation from a single image	50	2024
125	An intuitive tool for outlining objects in video sequences: Applications to augmented and diminished reality	49	2001
126	Location field descriptors: Single image 3d model retrieval in the wild	48	2019
127	Neural reprojection error: Merging feature learning and camera pose estimation	48	2021
128	Vision based 3D tracking and pose estimation for mixed reality	48	2007
129	An all-in-one solution to geometric and photometric calibration	47	2006
130	A stable real-time AR framework for training and planning in industrial environments	47	2004
131	Projection onto the manifold of elongated structures for accurate extraction	47	2015
132	S2dnet: Learning accurate correspondences for sparse-to-dense feature matching	47	2020
133	Linear and quadratic subsets for template-based tracking	46	2007
134	Systems and methods for normalizing an image	46	2019
135	Gaussian frosting: Editable complex radiance fields with real-time rendering	45	2024
136	Model retrieval for objects in images using field descriptors	45	2022
137	Simultaneous Recognition and Homography Extraction of Local Patches with a Simple Linear Classifier	44	2008
138	Learning to align semantic segmentation and 2.5 d maps for geolocalization	43	2017
139	Thick boundaries in binary space and their influence on nearest-neighbor search	43	2012
140	Ho-3d_v3: Improving the accuracy of hand-object annotations of the ho-3d dataset	42	2021
141	Three-dimensional pose estimation of symmetrical objects	42	2019
142	3d object detection and pose estimation of unseen objects in color images with local surface embeddings	41	2020
143	Polyhedral object detection and pose estimation for augmented reality applications	41	2002
144	Pose-specific non-linear mappings in feature space towards multiview facial expression recognition	41	2017
145	Human body pose recognition using spatio-temporal templates	39	2005
146	Bevcontrast: Self-supervision in bev space for automotive lidar point clouds	37	2024
147	Visual Golf Club Tracking for Enhanced Swing Analysis Tools	36	2003
148	CorNet: generic 3D corners for 6D pose estimation of new objects without retraining	35	2019
149	Detecting stable keypoints from events through image gradient prediction	35	2021
150	In-hand 3d object scanning from an rgb sequence	35	2023
151	Predicting people’s 3D poses from short sequences	35	2015
152	Smart hypothesis generation for efficient and robust room layout estimation	35	2020
153	General 3D Room Layout from a Single View by Render-and-Compare	34	2020
154	AssemblyNet: a novel deep decision-making process for whole brain MRI segmentation	33	2019
155	Handseg: An automatically labeled dataset for hand segmentation from depth images	33	2019
156	Monte Carlo Scene Search for 3D Scene Understanding	33	2021
157	From canonical poses to 3D motion capture using a single camera	32	2009
158	Robust data association for online applications	32	2003
159	Stable real-time interaction between virtual humans and real scenes	32	2003
160	3d pose refinement from reflections	31	2008
161	3-D head tracking via invariant keypoint learning	29	2012
162	A simple and powerful global optimization for unsupervised video object segmentation	29	2023
163	PIZZA: A powerful image-only zero-shot zero-CAD approach to 6 DoF tracking	29	2022
164	Handsformer: Keypoint transformer for monocular 3d pose estimation ofhands and object in interaction	28	2021
165	Point-and-shoot for ubiquitous tagging on mobile phones	28	2010
166	Computer Vision Methods for Registration: Mixing 3D Knowledge & 2D Correspondences for Accurate Image Composition	27	1998
167	On computer vision for augmented reality	25	2008
168	Gp2c: Geometric projection parameter consensus for joint 3d pose and focal length estimation in the wild	23	2019
169	Macarons: Mapping and coverage anticipation with rgb online self-supervision	23	2023
170	Scone: Surface coverage optimization in unknown environments by volumetric integration	23	2022
171	Appearance-based keypoint clustering	22	2009
172	Retexturing in the presence of complex illumination and occlusions	22	2007
173	Accurate Camera Registration in Urban Environments Using High-Level Feature Matching	21	2017
174	Augmenting deformable objects in real-time	21	2005
175	Fine hand segmentation using convolutional neural networks	21	2016
176	Golf club visual tracking for enhanced swing analysis tools	21	2003
177	Keypoint recognition using random forests and random ferns	21	2013
178	Extended keyframe detection with stable tracking for multiple 3D object tracking	20	2010
179	Real-time landing place assessment in man-made environments	18	2014
180	Recent advances in 3D object and hand pose estimation	18	2020
181	Visual correspondence hallucination	18	2021
182	3d facial pose estimation by image retrieval	17	2008
183	Filter learning for linear structure segmentation	17	2011
184	On the relevance of sparsity for image classification	17	2014
185	Predictor-corrector based pose detection	17	2018
186	Video-based in situ tagging on mobile phones	17	2011
187	An investigation of model bias in 3d face tracking	16	2005
188	Learning to better segment objects from unseen classes with unlabeled videos	16	2021
189	Monteboxfinder: Detecting and filtering primitives to fit a noisy point cloud	16	2022
190	Real-time interactive modeling and scalable multiple object tracking for AR	16	2012
191	ALCN: Adaptive local contrast normalization	15	2020
192	Layout estimation using planes	15	2022
193	X2Vision: 3D CT reconstruction from biplanar X-rays with deep structure prior	15	2023
194	Automatically Annotating Indoor Images with CAD Models via RGB-D Scans	14	2023
195	Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning	14	2020
196	Robust Data Association	14	2003
197	Robust Visual Golf Club Tracking	14	2016
198	A Summary of the 4th International Workshop on~ Recovering 6D Object Pose	13	2018
199	BOP challenge 2024 on model-based and model-free 6D object pose estimation	13	2025
200	Keypoint-based sampling for pose estimation	13	2023
201	Long-lived accurate keypoints in event streams	13	2022
202	Semantic segmentation for 3D localization in urban environments	13	2017
203	Approximated relative pose solvers for efficient camera motion estimation	12	2014
204	Beyond kernelboost	12	2014
205	Handseg: A dataset for hand segmentation from depth images	12	2017
206	Souvenirs du monde des montagnes	12	2009
207	You never get a second chance to make a good first impression: Seeding active learning for 3d semantic segmentation	12	2023
208	Geometric correspondence fields: Learned differentiable rendering for 3d pose refinement in the wild	11	2020
209	Method, system, and device for learned invariant feature transform for computer images	11	2020
210	Computer Vision–ACCV 2016	10	2017
211	Pose estimation of web-shared landscape pictures	10	2014
212	1st place solution for the uvo challenge on image-based open-world segmentation 2021	9	2021
213	Computer Vision–ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part III	9	2017
214	Kernelboost: Supervised learning of image features for classification	9	2015
215	Leaf segmentation under loosely controlled conditions	9	2015
216	Mcts with refinement for proposals selection games in scene understanding	9	2022
217	Monocular model-based 3d tracking of rigid objects	9	2005
218	Efficient 3D Tracking in Urban Environments with Semantic Segmentation	8	2017
219	Multi-finger grasping like humans	8	2022
220	Registration methods for harmonious integration of real world and computer generated objects	8	2000
221	Springer International Publishing: Cham, Switzerland, 2017	8	0
222	StructuRegNet: Structure-guided multimodal 2D-3D registration	8	2023
223	Alligat0r: Pre-training through co-visibility segmentation for relative camera pose regression	7	2025
224	Bundle adjustment for markerless body tracking in monocular video sequences	7	2003
225	Efficient condition-based representations for long-term visual localization	7	2018
226	HOC-Search: Efficient CAD Model and Pose Retrieval From RGB-D Scans	7	2024
227	Real-time augmented face	7	2003
228	Dense methods for image alignment with an application to 3D tracking	6	2014
229	Markov-based Silhouette Extraction for Three--Dimensional Body Tracking in Presence of Cluttered Background	6	2004
230	Monocular LSD-SLAM integration within AR system	6	2017
231	Nextbestpath: Efficient 3d mapping of unseen environments	6	2025
232	Boosting binary image descriptors	5	2012
233	Deep discrete flow, computer vision—ACCV 2016	5	2017
234	Model based augmentation and testing of an annotated hand pose dataset	5	2016
235	Pareto-optimal dictionaries for signatures	5	2010
236	S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation	5	2018
237	UNIT: Unsupervised online instance segmentation through time	5	2025
238	Augmented reality oculus rift	4	2016
239	HANDS18: Methods, techniques and applications for hand observation	4	2018
240	Monocular model-based 3D tracking of rigid objects	4	2005
241	Turning Augmented Reality into a media: Design exploration to build a dedicated visual language	4	2011