Search Results for author:
Found 30 papers, 15 papers with code
SLayR: Scene Layout Generation with Rectified Flow
We introduce SLayR, Scene Layout Generation with Rectified flow.
Spurfies: Sparse Surface Reconstruction using Local Geometry Priors
We introduce Spurfies, a novel method for sparse-view surface reconstruction that disentangles appearance and geometry information to utilize local geometry priors trained on synthetic data.
iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
We demonstrate the effectiveness of our method through extensive experiments on the Pascal3D and ObjectNet3D datasets and show that our approach outperforms the baselines for classification by $2-6\%$ in the in-domain and by $6-50\%$ in the OOD setting.
Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos
In a second step, the canonical poses and reconstructed meshes enable us to train a model for 3D pose estimation from a single image.
Neuroexplicit Diffusion Models for Inpainting of Optical Flow Fields
Deep learning has revolutionized the field of computer vision by introducing large scale neural networks with millions of parameters.
Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
When converting the occupancy maps back to depth estimates and comparing them with the raw LiDAR measurements, our method yields a MAE improvement of 30% to 52% on nuScenes and 53% on Waymo over other occupancy ground-truth data.
latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
We present latentSplat, a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture.
Recent Trends in 3D Reconstruction of General Non-Rigid Scenes
Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision.
Quantum-Hybrid Stereo Matching With Nonlinear Regularization and Spatial Pyramids
Our approach is hybrid (i. e., quantum-classical) and is compatible with modern D-Wave quantum annealers, i. e., it includes a quadratic unconstrained binary optimization (QUBO) objective.
Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation
However, none of the existing models enable disentangled generation to control the shape and appearance separately.
Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction
However, owing to the ill-posed nature of this problem, there has been no solution that can provide consistent, high-quality novel views from camera positions that are significantly different from the training views.
SimNP: Learning Self-Similarity Priors Between Neural Points
(1) We design the first neural point representation on a category level by utilizing the concept of coherent point clouds.
Recurrent Video Restoration Transformer with Guided Deformable Attention
Specifically, RVRT divides the video into multiple clips and uses the previously inferred clip feature to estimate the subsequent clip feature.
ERF: Explicit Radiance Field Reconstruction From Scratch
Robustly reconstructing such a volumetric scene model with millions of unknown variables from registered scene images only is a highly non-convex and complex optimization problem.
NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning
We let a feature encoding network and image reconstruction network compete with each other, such that the feature encoder tries to impede the image reconstruction with its generated descriptors, while the reconstructor tries to recover the input image from the descriptors.
Analysis and Mitigations of Reverse Engineering Attacks on Local Feature Descriptors
This poses a potential risk to user privacy.
Domain Adaptation of Learned Features for Visual Localization
We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons.
TLIO: Tight Learned Inertial Odometry
We show that our network, trained with pedestrian data from a headset, can produce statistically consistent measurement and uncertainty to be used as the update step in the filter, and the tightly-coupled system outperforms velocity integration approaches in position estimates, and AHRS attitude filter in orientation estimates.
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception.
Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
Future prediction is a fundamental principle of intelligence that helps plan actions and avoid possible dangers.
FusionNet and AugmentedFlowNet: Selective Proxy Ground Truth for Training on Unlabeled Images
The latter can be used as proxy-ground-truth to train a network on real-world data and to adapt it to specific domains of interest.
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.
Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow
Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology.
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations.
End-to-End Learning of Video Super-Resolution with Motion Compensation
We analyze the usage of optical flow for video super-resolution and find that common off-the-shelf image warping does not allow video super-resolution to benefit much from optical flow.
Lucid Data Dreaming for Video Object Segmentation
Our approach is suitable for both single and multiple object segmentation.
DeMoN: Depth and Motion Network for Learning Monocular Stereo
In this paper we formulate structure from motion as a learning problem.
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
Dense Pixel Correspondence Estimation
Optical Flow Estimation
+1
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
FlowNet: Learning Optical Flow with Convolutional Networks
Optical flow estimation has not been among the tasks where CNNs were successful.
