Search Results for author:
Found 43 papers, 18 papers with code
MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion
Structure-from-Motion (SfM), a task aiming at jointly recovering camera poses and 3D geometry of a scene given a set of images, remains a hard problem with still many open challenges despite decades of significant progress.
PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation
We showcase the potential of such an embroidered pose representation for (1) SMPL regression from image with optional text cue; and (2) on the task of fine-grained instruction generation, which consists in generating a text that describes how to move from one 3D pose to another (as a fitness coach).
UNIC: Universal Classification Models via Multi-teacher Distillation
Pretrained models have become a commodity and offer strong results on a broad range of tasks.
Purposer: Putting Human Motion Generation in Context
We present a novel method to generate human motion to populate 3D indoor scenes.
Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image.
Ranked #1 on
Human Mesh Recovery
on BEDLAM
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
After expanding the training set, we propose a training approach that leverages the specificities and the underlying geometry of this mix of real and synthetic images.
Cross-view and Cross-pose Completion for 3D Human Understanding
Human perception and understanding is a major domain of computer vision which, like many other vision subdomains recently, stands to gain from the use of large models pre-trained on large datasets.
Win-Win: Training High-Resolution Vision Transformers from Two Windows
It is 4 times faster to train than a full-resolution network, and it is straightforward to use at test time compared to existing approaches.
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
The main challenge lies in learning compact representations generalizable to unseen environments and in learning high-capacity perception modules capable of reasoning on high-dimensional input.
SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction
Recent hand-object interaction datasets show limited real object variability and rely on fitting the MANO parametric model to obtain groundtruth hand shapes.
PoseFix: Correcting 3D Human Poses with Natural Language
Automatically producing instructions to modify one's posture could open the door to endless applications, such as personalized coaching and in-home physical therapy.
SACReg: Scene-Agnostic Coordinate Regression for Visual Localization
Instead of encoding the scene coordinates into the network weights, our model takes as input a database image with some sparse 2D pixel to 3D coordinate annotations, extracted from e. g. off-the-shelf Structure-from-Motion or RGB-D data, and a query image for which are predicted a dense 3D coordinate map and its confidence, based on cross-attention.
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow
Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching or optical flow.
Ranked #1 on
Optical Flow Estimation
on KITTI 2012
PoseScript: Linking 3D Human Poses and Natural Language
Thirdly, we present a learned process for generating pose descriptions.
PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting
The discrete and compressed nature of the latent space allows the GPT-like model to focus on long-range signal, as it removes low-level redundancy in the input signal.
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
More precisely, we propose the pretext task of cross-view completion where the first input image is partially masked, and this masked content has to be reconstructed from the visible content and the second image.
PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling
It is simple, generic and versatile, as it can be plugged on top of any image-based model to transform it in a video-based model leveraging temporal information.
Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark
In order to investigate the consequences for visual localization, this paper focuses on understanding the role of image retrieval for multiple visual localization paradigms.
Learning Super-Features for Image Retrieval
Second, they are typically trained with a global loss that only acts on top of an aggregation of local features; by contrast, testing is based on local feature matching, which creates a discrepancy between training and testing.
Ranked #3 on
Image Retrieval
on ROxford (Medium)
PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors
In this paper, we propose to explicitly integrate two matching priors in a single loss in order to learn local descriptors without supervision.
Barely-Supervised Learning: Semi-Supervised Learning with very few labeled images
We propose a method to leverage self-supervised methods that provides training signal in the absence of confident pseudo-labels.
Leveraging MoCap Data for Human Mesh Recovery
In fact, we show that simply fine-tuning the batch normalization layers of the model is enough to achieve large gains.
Ranked #65 on
3D Human Pose Estimation
on MPI-INF-3DHP
Large-scale Localization Datasets in Crowded Indoor Spaces
In this paper, we introduce 5 new indoor datasets for visual localization in challenging real-world environments.
Multi-FinGAN: Generative Coarse-To-Fine Sampling of Multi-Finger Grasps
While there exists many methods for manipulating rigid objects with parallel-jaw grippers, grasping with multi-finger robotic hands remains a quite unexplored research topic.
SMPLy Benchmarking 3D Human Pose Estimation in the Wild
Predicting 3D human pose from images has seen great recent improvements.
SuperLoss: A Generic Loss for Robust Curriculum Learning
The key idea is to somehow estimate the importance (or weight) of each sample directly during training based on the observation that easy and hard samples behave differently and can therefore be separated.
Hard Negative Mixing for Contrastive Learning
Based on these observations, and motivated by the success of data mixing, we propose hard negative mixing strategies at the feature level, that can be computed on-the-fly with a minimal computational overhead.
DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild
We introduce DOPE, the first method to detect and estimate whole-body 3D human poses, including bodies, hands and faces, in the wild.
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set.
Mimetics: Towards Understanding Human Actions Out of Context
Our experiments show that (a) state-of-the-art 3D convolutional neural networks obtain disappointing results on such videos, highlighting the lack of true understanding of the human actions and (b) models leveraging body language via human pose are less prone to context biases.
R2D2: Reliable and Repeatable Detector and Descriptor
We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness.
Ranked #2 on
Camera Localization
on Aachen Day-Night benchmark
R2D2: Repeatable and Reliable Detector and Descriptor
In this work, we argue that salient regions are not necessarily discriminative, and therefore can harm the performance of the description.
Visual Localization by Learning Objects-Of-Interest Dense Match Regression
We introduce a novel CNN-based approach for visual localization from a single RGB image that relies on densely matching a set of Objects-of-Interest (OOIs).
PoTion: Pose MoTion Representation for Action Recognition
We use the human joints as these keypoints and term our Pose moTion representation PoTion.
Ranked #1 on
Skeleton Based Action Recognition
on J-HMDB
LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
We propose an end-to-end architecture for joint 2D and 3D human pose estimation in natural images.
3D Human Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+1
Joint Learning of Object and Action Detectors
dog and cat jumping, enabling to detect actions of an object without training with these object-actions pairs.
LCR-Net: Localization-Classification-Regression for Human Pose
We propose an end-to-end architecture for joint 2D and 3D human pose estimation in natural images.
Ranked #4 on
3D Multi-Person Pose Estimation (root-relative)
on MuPoTS-3D
(MPJPE metric)
3D Human Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+4
Action Tubelet Detector for Spatio-Temporal Action Localization
We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i. e., sequences of bounding boxes with associated scores.
Spatio-Temporal Action Localization
Temporal Action Localization
Human Action Localization with Sparse Spatial Supervision
We introduce an approach for spatio-temporal human action localization using sparse spatial supervision.
DeepMatching: Hierarchical Deformable Dense Matching
We introduce a novel matching algorithm, called DeepMatching, to compute dense correspondences between images.
Ranked #4 on
Dense Pixel Correspondence Estimation
on HPatches
Dense Pixel Correspondence Estimation
Optical Flow Estimation
Learning to track for spatio-temporal action localization
We present experimental results for spatio-temporal localization on the UCF-Sports, J-HMDB and UCF-101 action localization datasets, where our approach outperforms the state of the art with a margin of 15%, 7% and 12% respectively in mAP.
Spatio-Temporal Action Localization
Temporal Action Localization
+1
Learning to Detect Motion Boundaries
We compare the results obtained with several state-of-the-art optical flow approaches and study the impact of the different cues used in the random forest. Furthermore, we introduce a new dataset, the YouTube Motion Boundaries dataset (YMB), that comprises 60 sequences taken from real-world videos with manually annotated motion boundaries.
EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow
We propose a novel approach for optical flow estimation , targeted at large displacements with significant oc-clusions.
